Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T13:36:57.011451Z
Paper Citation Record · LEDGER
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
As of 4 August 2026, this Paper Citation Record lists 100 of 143 outbound references and 79 inbound Pith citation observations for arXiv:2410.02644.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-04T13:00:07.559162Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-10T06:15:00.866473Z
Reference resolution
100 of 143 outbound references displayed
- verified exact16
- verified fuzzy75
- unresolved3
- parse uncertain2
- malformed identifier0
- metadata mismatch4
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 0f302d2d-8f48-400d-a91e-a1a37ede8cce · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.386619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bc79f650-8870-4fe3-a6be-bacc541c3130 · outbound
This paper cites The 2023 Conference on Empirical Methods in Natural Language Processing , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents The 2023 Conference on Empirical Methods in Natural Language Processing , year=
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.286054Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a6bc1b27-ed66-4861-b6b5-53dfc31eae26 · outbound
This paper cites 33rd USENIX Security Symposium (USENIX Security 24) , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 33rd USENIX Security Symposium (USENIX Security 24) , year =
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.306569Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ed560cfa-2ff3-4421-8b6a-c551bfc12722 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.390538Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1d5ef2f3-ac26-4a49-bf95-33985087bd25 · outbound
This paper cites an unresolved cited work.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T13:36:57.392436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 44b007c3-9e94-4d36-8969-c3b9e1018812 · outbound
This paper cites an unresolved cited work.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Unresolved cited work
Reference 7
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-12T13:36:57.394618Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b568cfde-5ca2-463c-ad11-82e691a11224 · outbound
This paper cites 2022 , journal=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2022 , journal=
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.396676Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 779206c7-b680-4b78-8232-841c6fbcf1c8 · outbound
This paper cites NeurIPS ML Safety Workshop , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents NeurIPS ML Safety Workshop , year =
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.398854Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2bc061a7-f2b4-45cb-ab3c-7e98aa2a0b7e · outbound
This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Retrieval-augmented generation for knowledge-intensive NLP tasks , year =
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.401410Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 36b5d786-8e4b-421f-b426-f9c4cc62d21a · outbound
This paper cites The Impact of Reasoning Step Length on Large Language Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents The Impact of Reasoning Step Length on Large Language Models
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.403448Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3ff12715-2172-436c-9089-042dfc3cc232 · outbound
This paper cites 2023 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , eprint=
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.405794Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 60e0e7c4-d376-4913-a2bc-fbbda42421aa · outbound
This paper cites 2022 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2022 , eprint=
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.408040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation dcb0c349-20d4-4e96-b6c4-856022c4fd41 · outbound
This paper cites A Survey of Man In The Middle Attacks , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents A Survey of Man In The Middle Attacks , year=
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.410502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9bc35b71-d36d-4550-85e6-ec9e87a858d4 · outbound
This paper cites arXiv , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents arXiv , year=
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.412679Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ee261799-e044-4050-8f7d-2f8dcd2eae00 · outbound
This paper cites 2023 , journal=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , journal=
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.414966Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 67379ddb-5c1e-4b90-8a2d-04e5dd19acde · outbound
This paper cites 2024 , publisher=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , publisher=
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.418292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9aad6066-ab50-4788-9adf-b7d5a532b439 · outbound
This paper cites GPT-4 Technical Report.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents GPT-4 Technical Report
Reference 23
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T13:36:57.083241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 790bd615-7318-42fe-9894-6a94e1347cab · outbound
This paper cites OpenAI Blog , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents OpenAI Blog , year=
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.423242Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e691c624-7637-4a70-a45d-5b34401096c1 · outbound
This paper cites OpenAI Blog , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents OpenAI Blog , year=
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.425373Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d48e9712-fed9-47e9-8667-6af7e6b8dc6e · outbound
This paper cites 2023 , url =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , url =
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.427618Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 29655ecd-61e3-48df-8443-afd739120084 · outbound
This paper cites URL https://arxiv , volume=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents URL https://arxiv , volume=
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.429490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 56332c25-5aef-4489-adf9-cc8017a3f569 · outbound
This paper cites Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track , year=
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.431972Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 67e9e9ee-ac13-4044-b597-0de93e0662cd · outbound
This paper cites Rab: Provable robustness against backdoor attacks , booktitle =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Rab: Provable robustness against backdoor attacks , booktitle =
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.434187Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 45278ad0-0e0f-4175-9f39-23c5fd282962 · outbound
This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Advances in Neural Information Processing Systems (NeurIPS) , year =
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.436422Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 718ed8a2-39f6-4138-a81d-192d70de2124 · outbound
This paper cites International Conference on Machine Learning , pages=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents International Conference on Machine Learning , pages=
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.438989Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d0f3c18-b513-4fd4-a1fc-3e7ad22a1cb5 · outbound
This paper cites Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Reference 33
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.087415Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 39a82801-c1da-499d-a91c-960c8bd5de61 · outbound
This paper cites Advances in neural information processing systems , volume=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Advances in neural information processing systems , volume=
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.443580Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5eb016b2-c542-4bc8-88ff-d978c58e2e1d · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.445845Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 82eb00d2-ba63-4410-8d84-50c63fb22330 · outbound
This paper cites Proceedings of the 36th International Conference on Neural Information Processing Systems , articleno =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 36th International Conference on Neural Information Processing Systems , articleno =
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.448136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eea54bcc-8303-425d-b797-14d2be0a6ba0 · outbound
This paper cites an unresolved cited work.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T13:36:57.450651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d9288bce-1a14-4297-afc2-22cf9e2252dc · outbound
This paper cites In Advances in Neural Information Processing Systems (NeurIPS) , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents In Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.453125Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f2c942f7-b58d-480c-8a84-6727682591a2 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.455661Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c237b50d-6f1e-44d0-8e41-436c01c918e5 · outbound
This paper cites 2023 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , eprint=
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.458116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 23b9cdf5-1b36-4836-b2c6-5062c0d25248 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.460947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 16714606-bb46-4f9f-864b-ad282d9f20c9 · outbound
This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.463640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2f71694d-5a19-4430-83b5-84738df4d9e0 · outbound
This paper cites 2024 IEEE Security and Privacy Workshops (SPW) , pages=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 IEEE Security and Privacy Workshops (SPW) , pages=
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.468044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4909b3dc-7415-47a3-8e01-abed55539dd2 · outbound
This paper cites Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security , pages=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security , pages=
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.470970Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 714092db-543b-4077-8064-f7c5ded6668c · outbound
This paper cites an unresolved cited work.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Unresolved cited work
Reference 55
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-12T13:36:57.473728Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8facc36f-a5a2-49cf-baf1-195b89840d7a · outbound
This paper cites 2023 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , eprint=
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.476123Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 42884a1b-9c76-497e-91ae-a05988b6aec7 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.230235Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a3177c5e-adc6-4f7b-b5d3-9c03b7009ff1 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.232677Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b53363d7-4ada-4724-ab57-0bf89504a187 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.235194Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d753c699-05b2-49a5-9237-cd9c06be9a4b · outbound
This paper cites Maddison and Tatsunori Hashimoto , booktitle=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Maddison and Tatsunori Hashimoto , booktitle=
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.237965Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f2c018c3-9266-4a2f-af8f-fe2126da702e · outbound
This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Reference 63
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.091607Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1e068fd6-7710-4884-aa34-8b5261a7be38 · outbound
This paper cites arXiv , primaryClass=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents arXiv , primaryClass=
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.242670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d4697392-22a7-4cb7-b3af-e5b070aaf893 · outbound
This paper cites EMNLP , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents EMNLP , year=
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.244789Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a4221a37-ab21-4d65-a0b7-d25be155837e · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.246993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e76ef73b-ec20-409c-a705-b169e65424b9 · outbound
This paper cites 2024 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , eprint=
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.249277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4864ee39-8aa9-4b6c-a40b-80df91346a4c · outbound
This paper cites 2024 , url =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , url =
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.251499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5b8bc126-fdf0-44a6-b15d-8ebccc43d7a6 · outbound
This paper cites 2024 , howpublished =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , howpublished =
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.254278Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 25d40eeb-37e6-40e4-869d-365084a8aa50 · outbound
This paper cites 2024 , howpublished =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , howpublished =
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.256662Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation be2ef07f-56b3-49e5-b225-c33b68dc819f · outbound
This paper cites 2024 , note =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2024 , note =
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.259178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e1879d31-0400-4eae-8278-7624b48c6dbc · outbound
This paper cites Proceedings of the 41st International Conference on Machine Learning (ICML) , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 41st International Conference on Machine Learning (ICML) , year =
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.261577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 52fcc9d6-e93d-4a07-a017-3e1361207d0b · outbound
This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year =
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.264141Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 406140e4-372b-4156-93f3-20e9408824e8 · outbound
This paper cites 2023 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , eprint=
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.266402Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8c90f575-be9e-40f6-8527-75f84d83b4ac · outbound
This paper cites 2023 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2023 , eprint=
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.268596Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 79615d7b-d279-4074-b654-f26f4e01d70f · outbound
This paper cites Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), Track on Datasets and Benchmarks , year =.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), Track on Datasets and Benchmarks , year =
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.271160Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9b6057ff-e9d7-495b-8b22-87d0bee3b9ba · outbound
This paper cites Adversaries Can Misuse Combinations of Safe Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Adversaries Can Misuse Combinations of Safe Models
Reference 77
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.096155Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c5cfca29-b7e8-4099-9d89-5061872ffee6 · outbound
This paper cites Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.277453Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 122f477c-9639-4c41-9f58-9118411cabfa · outbound
This paper cites Available at SSRN 5062105 , year=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Available at SSRN 5062105 , year=
Reference 80
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.280590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 818626af-4551-4cad-b6fb-c1f92dc006ef · outbound
This paper cites 2025 , eprint=.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents 2025 , eprint=
Reference 82
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.283329Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f9093915-e172-4168-bc35-98f8fc47c380 · outbound
This paper cites Conversational Health Agents: A Personalized LLM-Powered Agent Framework.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Conversational Health Agents: A Personalized LLM-Powered Agent Framework
Reference 84
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.100600Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e5f8d000-7b8b-4456-aad3-0420bf5a8488 · outbound
This paper cites Detecting language model attacks with perplexity.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Detecting language model attacks with perplexity
Reference 85
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.288599Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f90f8c21-f61d-4c24-af1e-173af01533a0 · outbound
This paper cites Model leaderboards.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Model leaderboards
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.290937Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0b880e81-9f9c-4e1c-be29-577b0d763819 · outbound
This paper cites Claude 3.5 sonnet.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Claude 3.5 sonnet
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.293570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 65b6d7ca-6b07-48b2-97ac-575075dd1ca0 · outbound
This paper cites Api-blend: A comprehensive corpora for training and benchmarking api llms.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Api-blend: A comprehensive corpora for training and benchmarking api llms
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.296158Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ddfb43f4-7aa4-42eb-826c-12d86e383b46 · outbound
This paper cites Branch, Jonathan Rodriguez Cefalu, Jeremy McHugh, Leyla Hujer, Aditya Bahl, Daniel del Castillo Iglesias, Ron Heichman, and Ramesh Darwishi.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Branch, Jonathan Rodriguez Cefalu, Jeremy McHugh, Leyla Hujer, Aditya Bahl, Daniel del Castillo Iglesias, Ron Heichman, and Ramesh Darwishi
Reference 89
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.298798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 79e8cdc7-e4e5-4d25-9bdf-430e16a0006a · outbound
This paper cites BadPrompt: Backdoor Attacks on Continuous Prompts.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents BadPrompt: Backdoor Attacks on Continuous Prompts
Reference 90
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.104780Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5cfcf83a-be81-421e-82a6-f48ab34cadbc · outbound
This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Reference 91
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.109054Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 05eb6d93-f0c7-45f9-9bfc-5af1098e3465 · outbound
This paper cites A survey of man in the middle attacks.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents A survey of man in the middle attacks
Reference 92
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.070227Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4b602537-a16a-4161-afb9-b6986f99baac · outbound
This paper cites Agentdojo: A dynamic environment to evaluate attacks and defenses for llm agents.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Agentdojo: A dynamic environment to evaluate attacks and defenses for llm agents
Reference 93
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.308753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 418ce3f1-111c-4220-9881-b5fd75246a8f · outbound
This paper cites The Philosopher's Stone: Trojaning Plugins of Large Language Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents The Philosopher's Stone: Trojaning Plugins of Large Language Models
Reference 94
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.113393Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0f4ef4d6-091d-409d-8f46-77d68bdc66bb · outbound
This paper cites The Llama 3 Herd of Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents The Llama 3 Herd of Models
Reference 95
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T13:36:57.117714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b0592dd1-d8a1-4607-b72d-b53eb871acc1 · outbound
This paper cites Ai prompt optimization services.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Ai prompt optimization services
Reference 96
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.316599Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2c45d253-0926-4951-9c1d-96869f4ee9b3 · outbound
This paper cites Openagi: When llm meets domain experts.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Openagi: When llm meets domain experts
Reference 97
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.318977Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ec95e0ca-d760-45cf-a916-cf41f788db28 · outbound
This paper cites LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem
Reference 98
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.122714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f0784c72-8e7a-48d6-83b5-dd9cd5bd7ac4 · outbound
This paper cites Rapidapi hub.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Rapidapi hub
Reference 99
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.323414Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1934347b-aba6-4d28-bec7-3e0f3d9e27af · outbound
This paper cites Using gpt-eliezer against chatgpt jailbreaking.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Using gpt-eliezer against chatgpt jailbreaking
Reference 100
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.325580Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eede8d70-ef24-465d-a0af-b6e361821213 · outbound
This paper cites Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
Reference 101
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.327735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 04b35710-f305-451b-b9a3-f3f84fc19f76 · outbound
This paper cites Securing llm systems against prompt injection.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Securing llm systems against prompt injection
Reference 102
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.329842Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4752e341-a23b-48bc-aacb-e67578052f9e · outbound
This paper cites Trustagent: Towards safe and trustworthy llm-based agents through agent constitution.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Trustagent: Towards safe and trustworthy llm-based agents through agent constitution
Reference 103
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.331960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6ab6ae8f-db1a-4e24-b73b-2ebe41667118 · outbound
This paper cites Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
Reference 104
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.127277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 69492c6f-88b4-4c7f-ba37-891b44b0c21b · outbound
This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Reference 105
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T13:36:57.131425Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b8947ddd-2ece-4614-ac5d-0119c1e25b9b · outbound
This paper cites Baseline defenses for adversarial attacks against aligned language models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Baseline defenses for adversarial attacks against aligned language models
Reference 106
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.339296Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 98f74d82-578d-4bb2-a54b-df80e4f273dc · outbound
This paper cites Mixtral of Experts.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Mixtral of Experts
Reference 107
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T13:36:57.135277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ccd147ee-5171-42fc-b2b9-7a45c472609c · outbound
This paper cites The impact of reasoning step length on large language models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents The impact of reasoning step length on large language models
Reference 108
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.343898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bf93ba74-5279-4adf-8c14-ab37143ef9c2 · outbound
This paper cites Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
Reference 109
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.139599Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5d68421d-231b-47bb-85d0-4d32dee11f78 · outbound
This paper cites an unresolved cited work.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Unresolved cited work
Reference 110
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T13:36:57.348102Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 88eb2081-cff7-472f-992f-49cf9235224a · outbound
This paper cites Backdoor Attacks for In-Context Learning with Language Models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Backdoor Attacks for In-Context Learning with Language Models
Reference 111
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.144086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c6080923-ea21-4dbd-b0f0-733b44e75a9a · outbound
This paper cites Exploiting programmatic behavior of llms: Dual-use through standard security attacks.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Exploiting programmatic behavior of llms: Dual-use through standard security attacks
Reference 112
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.352904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 06fbc4d5-d866-4fb1-87f7-168fec7b0d3f · outbound
This paper cites Large language models are zero-shot reasoners.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Large language models are zero-shot reasoners
Reference 113
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.355017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation be92c361-22d2-4b27-8e99-5c0bd86a4f4c · outbound
This paper cites Random sequence enclosure.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Random sequence enclosure
Reference 114
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.356943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2b1d651c-c43e-4f8d-84d8-62c3043f4f55 · outbound
This paper cites Instruction defense.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Instruction defense
Reference 115
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.358841Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6e07628d-a822-4c4a-b687-8646a1d60705 · outbound
This paper cites Sandwitch defense.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Sandwitch defense
Reference 116
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.360790Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 10a29236-5198-4d1d-92dc-54614efc2e05 · outbound
This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt\.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt\
Reference 117
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.362797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 150e10ab-4830-4988-b780-e4a23cb89c6c · outbound
This paper cites BadEdit: Backdooring large language models by model editing.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents BadEdit: Backdooring large language models by model editing
Reference 118
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.148449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4bfe2f0c-2475-4567-8ba0-f5722eb71e90 · outbound
This paper cites Prompt Injection attack against LLM-integrated Applications.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Prompt Injection attack against LLM-integrated Applications
Reference 119
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T13:36:57.152360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 75180926-31e7-48b6-8c5a-b09d45f77d5e · outbound
This paper cites Formalizing and benchmarking prompt injection attacks and defenses.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Formalizing and benchmarking prompt injection attacks and defenses
Reference 120
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T13:36:57.369859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 564029f0-adab-4ae5-817d-cb12edf903c8 · outbound
This paper cites A Language Agent for Autonomous Driving.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents A Language Agent for Autonomous Driving
Reference 121
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.157257Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 54681231-d39d-43fa-abed-4a4e27a6b38b · outbound
This paper cites Membership Inference Attacks against Language Models via Neighbourhood Comparison.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Membership Inference Attacks against Language Models via Neighbourhood Comparison
Reference 122
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.161301Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
Observation 603e05ed-08a7-43b6-8706-c1438a0a5bc4 · inbound
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 148
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-14T22:23:14.851605Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d91f052f-3431-4065-99fd-1609a0f26500 · inbound
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks cites this paper.
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T13:00:07.559162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4b863666-0c3f-49c8-9e41-01d8a6bf099b · inbound
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 241
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T03:42:21.957828Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a86d7c8c-49a7-4c9f-af6d-dbf61872b44a · inbound
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T07:06:38.155316Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 80906609-7ff6-4c86-a749-eff58872a302 · inbound
Formal Policy Enforcement for Real-World Agentic Systems cites this paper.
Formal Policy Enforcement for Real-World Agentic Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 68
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T21:10:18.616981Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation aec9eeee-152b-4c8c-a487-aaf4d4ac4ea3 · inbound
Tracking Capabilities for Safer Agents cites this paper.
Tracking Capabilities for Safer Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 86
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T18:36:29.214193Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 383ed561-f98d-44d8-8afe-f452e8fc9064 · inbound
Security Considerations for Multi-agent Systems cites this paper.
Security Considerations for Multi-agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 160
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T14:15:55.241630Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d5cdd15b-74a5-47f8-8389-8f3eaed0b352 · inbound
Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety cites this paper.
Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 71
- Resolution
- unresolved
- no resolver link, observed 2026-07-15T13:17:48.274611Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02aa3dc2-b50c-4160-a76a-cc3cad55bcbd · inbound
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents cites this paper.
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T19:43:11.211245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation df85d7a4-f558-4be6-b7e9-f0ae57939c78 · inbound
DRAFT: Task Decoupled Latent Reasoning for Agent Safety cites this paper.
DRAFT: Task Decoupled Latent Reasoning for Agent Safety Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T02:27:09.827837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8ce834dd-2314-4dcf-9bef-42884f498a57 · inbound
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw cites this paper.
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d2d7af40-0f65-4ce1-8efa-7d98ee9266a0 · inbound
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail? cites this paper.
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail? Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5a89ba85-c69e-494e-babe-c6ce8fe8cc3d · inbound
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems cites this paper.
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 97fbf649-0757-4a00-8f62-fcc7ba4c200f · inbound
SoK: Security of Autonomous LLM Agents in Agentic Commerce cites this paper.
SoK: Security of Autonomous LLM Agents in Agentic Commerce Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 136
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5b50b6df-5254-4025-a524-0b2a1668e4a9 · inbound
SafeAgent: A Runtime Protection Architecture for Agentic Systems cites this paper.
SafeAgent: A Runtime Protection Architecture for Agentic Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0ddaf1e2-81bf-426e-86b4-49b045d148a0 · inbound
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ef20789c-070a-4fdd-a413-b2c8ed6a5a15 · inbound
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T00:53:53.100451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4a890388-5b46-4deb-9658-29857e30f8c7 · inbound
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T15:56:49.042516Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c9a4de58-d68a-4012-99e7-25c776c3f130 · inbound
EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation cites this paper.
EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f5d4db5e-bc0a-45ed-88ce-0f33252a5f36 · inbound
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework cites this paper.
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 94
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2c46d0cc-30d8-4c7f-b727-9c697c765251 · inbound
SUDP: Secret-Use Delegation Protocol for Agentic Systems cites this paper.
SUDP: Secret-Use Delegation Protocol for Agentic Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d09f1eb8-0714-48c7-be3e-c0b36e656745 · inbound
SUDP: Secret-Use Delegation Protocol for Agentic Systems cites this paper.
SUDP: Secret-Use Delegation Protocol for Agentic Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-25T06:45:26.023203Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 54aaa9b7-e127-40d9-ab72-3a80321fd970 · inbound
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents cites this paper.
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 29d7e2a3-0c59-402d-8a22-bf7f0d12dfd3 · inbound
Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis cites this paper.
Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation de3d01fa-3d46-4d4a-88e4-9be6363380a1 · inbound
Toward a Principled Framework for Agent Safety Measurement cites this paper.
Toward a Principled Framework for Agent Safety Measurement Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c0053466-8274-4ab9-abdb-657c0a7bda7f · inbound
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration cites this paper.
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 94
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b5810d7c-686b-4ece-abfb-02148e484e0d · inbound
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration cites this paper.
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 92
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T17:32:41.616870Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 852de75c-593c-432b-ac3e-39367ae2c975 · inbound
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection cites this paper.
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a01be466-91d5-4509-9d5e-3ad5b58754b0 · inbound
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents cites this paper.
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eb61d9f9-966d-41ea-8b27-ded3e3d28a66 · inbound
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents cites this paper.
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bfeb2fe0-18cf-4594-aa68-3f509e5bae6e · inbound
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills cites this paper.
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 61
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 60c9c6e5-77ac-428d-90fa-e0414e5d0b22 · inbound
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation cites this paper.
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b66ae53d-4030-416d-86b1-a123a83af239 · inbound
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability cites this paper.
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 154
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 66d6c21d-242a-41ad-b550-54312eee829f · inbound
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions cites this paper.
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ae411fa1-30d3-4b0d-8228-3d205ef23c2a · inbound
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions cites this paper.
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 51
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 382ed6b3-1542-4d6f-afaf-849e4b57a387 · inbound
Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem cites this paper.
Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 65
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 61bb0ed7-b66b-49c4-b302-03bfd9929683 · inbound
AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey cites this paper.
AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 167
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0a0a65c4-dbb7-4b25-a040-9266f4c41a94 · inbound
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks cites this paper.
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b2f730d1-d62b-45b5-954f-adba4da6f05e · inbound
When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents cites this paper.
When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 28
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4d6708fe-e7c5-4501-b309-490527c55fd7 · inbound
When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents cites this paper.
When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 28
- Resolution
- malformed identifier
- local_arxiv, observed 2026-05-13T07:02:27.486532Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1cd6a57a-8fc5-47c7-81e6-1da15b053b25 · inbound
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium cites this paper.
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 90
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation de632d70-5855-402d-989b-87f693080b84 · inbound
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation cites this paper.
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 54
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T13:36:57.477107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d17932e8-2a7f-4466-ae88-688e02e2d13a · inbound
On the dilaton gravity of analogue black holes cites this paper.
On the dilaton gravity of analogue black holes Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T17:06:32.429160Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce90546b-7f3c-4f3d-b050-5ebed62c8b0f · inbound
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw cites this paper.
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T00:57:00.658454Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f25138af-0b06-4b00-999e-b7bd72b716a9 · inbound
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces cites this paper.
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 92
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T05:12:17.923596Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation de946cb4-f319-40ef-b06a-9678e787f9a9 · inbound
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning cites this paper.
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 45
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T20:19:27.914873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 082c934c-a85d-443c-a90d-18a8e8127465 · inbound
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents cites this paper.
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T18:22:33.611327Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 35fd11f3-8d94-423b-b379-07f2ba011b0a · inbound
Web Agents Should Adopt the Plan-Then-Execute Paradigm cites this paper.
Web Agents Should Adopt the Plan-Then-Execute Paradigm Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T02:49:41.555150Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d6bdd1a1-6a24-4dad-b7be-123f13f5c09c · inbound
Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.
Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 65
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T01:43:57.025992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7dce6993-0dd2-4be1-bfe2-2222263e072b · inbound
ADR: An Agentic Detection System for Enterprise Agentic AI Security cites this paper.
ADR: An Agentic Detection System for Enterprise Agentic AI Security Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T13:18:18.193908Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 80704353-e5d1-47cb-8147-d0976cf8267d · inbound
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback cites this paper.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.612366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ad9e6848-9d7a-4502-90f6-7a721179e310 · inbound
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection cites this paper.
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T10:03:14.272195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3abaaa3f-07ea-4a7c-8149-47e9683f98a5 · inbound
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection cites this paper.
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T18:55:00.640215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cffb1fae-e727-45d1-b564-eb2038453ba2 · inbound
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks cites this paper.
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T08:58:10.419292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 99bb09ca-6559-40ec-9e3f-ff3d851d9dad · inbound
Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents cites this paper.
Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T18:03:48.492926Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cbc38eb6-123c-4ced-9849-cac69edd6ec2 · inbound
Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities cites this paper.
Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 64
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T11:23:20.626000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 58f613b7-deaf-4efd-8e30-e52ea894b7c1 · inbound
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs cites this paper.
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 246
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T01:07:30.248530Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 09e1267f-661c-41b4-9892-b98d517b7455 · inbound
Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents cites this paper.
Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T01:47:31.925589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b910bf93-5ad1-4264-943d-49f0d57d17fb · inbound
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems cites this paper.
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T12:28:07.770953Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d6fe91d-88f5-42c3-beef-2a4420bf1e03 · inbound
Order Is Not Control cites this paper.
Order Is Not Control Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 40
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T14:08:21.838404Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6ac1b8d2-3149-4362-adf8-b998fb7df876 · inbound
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents cites this paper.
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T15:48:35.862017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e52ed15b-c60a-434c-88e1-4a67a4e0b550 · inbound
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails cites this paper.
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T16:58:43.519152Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 12b64d33-8fad-4c59-8946-f757bd2760ff · inbound
AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents cites this paper.
AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T16:48:40.465201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f1ba769d-caec-44da-8f08-5d421976b0d7 · inbound
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning cites this paper.
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 25
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T04:59:36.383138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 96506f03-a1e9-4bf4-bd5f-b681860313f0 · inbound
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems cites this paper.
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T11:19:50.263486Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cde73945-4960-405f-8903-f51910e0c308 · inbound
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents cites this paper.
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 129
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T14:09:53.034398Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 52618e1e-d08c-4721-9348-cff9c83832eb · inbound
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens cites this paper.
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T12:35:44.115038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8ecaf8ac-cb16-46f9-b9d3-1c1419778c20 · inbound
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows cites this paper.
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T07:06:19.120982Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5f5d9c08-2fe4-495f-bbb6-56a7c896eafc · inbound
MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents cites this paper.
MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T01:34:16.008911Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 59aa6030-0cdd-429a-b803-5ec70a09ab28 · inbound
How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in Practice cites this paper.
How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in Practice Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 119
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T20:20:09.527207Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aaf8b5b4-0d15-4981-a825-f1342f6301ed · inbound
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? cites this paper.
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T16:32:04.097021Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d115aadd-394f-482b-9a3e-b7b035fc542e · inbound
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems cites this paper.
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T15:28:30.469167Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 48bcac9d-1961-437b-a039-51f235b0dcad · inbound
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests cites this paper.
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T09:30:51.290701Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 245c14bd-6156-45b4-9fb3-078ac453d8bd · inbound
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents cites this paper.
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T22:03:09.995584Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bf33890-f0bd-4a1b-9675-fcbf3357c1a8 · inbound
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems cites this paper.
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T03:01:04.949244Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d2ac8360-d29e-428f-bcd8-2bf4a99ab2e3 · inbound
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications cites this paper.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.246438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03156622-021f-43a8-884d-63311c262b19 · inbound
GPT-Red: Automated Red Teaming via Self-Play at Scale cites this paper.
GPT-Red: Automated Red Teaming via Self-Play at Scale Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T01:12:44.195947Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1aa731a2-36a4-44e4-85b0-818ff43ed3db · inbound
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems cites this paper.
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:51:16.966876Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3a91b1a6-7b23-44d8-b540-58c48773e4f9 · inbound
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges cites this paper.
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T00:55:23.734394Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.