Paper Citation Record · LEDGER

Attack and defense techniques in large language models: A survey and new perspectives

As of 19 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 6 inbound Pith citation observations for arXiv:2505.00976.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.00976 v1

Coverage vector

measured 92 of 92 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:33:06.641038Z

measured 98 of 98 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:21:42.232920Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-18T04:25:52.249755Z

Reference resolution

92 of 92 outbound references displayed

verified exact3
verified fuzzy29
unresolved60
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1e422e49-a87e-4006-b101-d5f76b4caf28 · outbound

This paper cites , Wu, C.S.,.

Attack and defense techniques in large language models: A survey and new perspectives , Wu, C.S.,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.182806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbf812c1-fde7-419a-8add-e7ffec302cdb · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Attack and defense techniques in large language models: A survey and new perspectives Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.191534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3acc73-d4d8-4ba6-ac72-ded3a3932b1a · outbound

This paper cites Model Leeching: An Extraction Attack Targeting LLMs.

Attack and defense techniques in large language models: A survey and new perspectives Model Leeching: An Extraction Attack Targeting LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.195521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f0f2944-a96e-4e9e-be11-8302fd9a1064 · outbound

This paper cites Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples.

Attack and defense techniques in large language models: A survey and new perspectives Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.199548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10126db0-cc96-4bc8-a586-a5e93fd8da4b · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.203546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc38e493-c4ae-4377-8787-32dda7140026 · outbound

This paper cites A survey on evaluatio n of large language models.

Attack and defense techniques in large language models: A survey and new perspectives A survey on evaluatio n of large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.210792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25d9cb13-5084-4004-b4fb-666ef0475e3a · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Attack and defense techniques in large language models: A survey and new perspectives Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.214422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4d2085d-33bf-4df0-b823-6d95090b1dc7 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

Attack and defense techniques in large language models: A survey and new perspectives StruQ: Defending Against Prompt Injection with Structured Queries

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.218907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f21019-93a2-46b5-a84f-a84aecbf53cf · outbound

This paper cites Denoising adversari al autoen- coders.

Attack and defense techniques in large language models: A survey and new perspectives Denoising adversari al autoen- coders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.223049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87a2475c-dfaa-4bdf-98c6-a76bf7242767 · outbound

This paper cites Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems.

Attack and defense techniques in large language models: A survey and new perspectives Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.226603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 739bd4af-e9e9-497a-8616-b44af9a634bd · outbound

This paper cites Security and priva cy chal- lenges of large language models: A survey.

Attack and defense techniques in large language models: A survey and new perspectives Security and priva cy chal- lenges of large language models: A survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.230512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae53b5b2-f96a-4e99-83b5-b77fb18fed7e · outbound

This paper cites Attack Prompt Generation for Red Teaming and Defending Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives Attack Prompt Generation for Red Teaming and Defending Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.234002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d0a2118-9831-41c8-bb80-712bf8f215f9 · outbound

This paper cites Masterkey: Automated jailbreaking of large language model chatbots, in: Proc.

Attack and defense techniques in large language models: A survey and new perspectives Masterkey: Automated jailbreaking of large language model chatbots, in: Proc

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.238075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62633ba8-85fd-410d-838d-af5cc5a03607 · outbound

This paper cites A comprehensi ve sur- vey of attack techniques, implementation, and mitigation strategies in large language models, in: International Conference on Ubi quitous Security, Springer.

Attack and defense techniques in large language models: A survey and new perspectives A comprehensi ve sur- vey of attack techniques, implementation, and mitigation strategies in large language models, in: International Conference on Ubi quitous Security, Springer

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.242121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d780866-3088-47c2-9f54-4f63a1fad5bb · outbound

This paper cites Recent advance s in robust optimization: An overview.

Attack and defense techniques in large language models: A survey and new perspectives Recent advance s in robust optimization: An overview

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.245625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f81ab0-1a0d-46af-8844-a5ef548ae397 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.249505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff52a8ad-ed36-4f9a-a701-b9b39a0181aa · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.252868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc5462db-3372-4955-b149-0dbdef650516 · outbound

This paper cites The ethics of c hatgpt in medicine and healthcare: a systematic review on large language mod- els (llms).

Attack and defense techniques in large language models: A survey and new perspectives The ethics of c hatgpt in medicine and healthcare: a systematic review on large language mod- els (llms)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.712667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 340c8833-e0e3-42c0-b24a-de58f63238d4 · outbound

This paper cites Cater: Intellectual property protection on text generation apis via conditional watermarks.

Attack and defense techniques in large language models: A survey and new perspectives Cater: Intellectual property protection on text generation apis via conditional watermarks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.699528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1504c4a4-a586-43a1-827c-d93e70a58d78 · outbound

This paper cites IEEE Transactions on Pattern Analysis and Ma chine Intelligence.

Attack and defense techniques in large language models: A survey and new perspectives IEEE Transactions on Pattern Analysis and Ma chine Intelligence

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.726345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 405b8f57-108f-4574-b03b-68d4bb27621d · outbound

This paper cites Are Large Pre-Trained Language Models Leaking Your Personal Information?.

Attack and defense techniques in large language models: A survey and new perspectives Are Large Pre-Trained Language Models Leaking Your Personal Information?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.271376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a30be89-fa7a-4a30-9b64-a94bf5829f2b · outbound

This paper cites Attention Tracker: Detecting Prompt Injection Attacks in LLMs.

Attack and defense techniques in large language models: A survey and new perspectives Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.274995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7138ac-0e2b-48cc-9d2b-eb2b1dbf9ec7 · outbound

This paper cites The use and misuse of pre-trained generative large language models in reli- ability engineering, in: 2024 Annual Reliability and Maint ainability Symposium (RAMS), IEEE.

Attack and defense techniques in large language models: A survey and new perspectives The use and misuse of pre-trained generative large language models in reli- ability engineering, in: 2024 Annual Reliability and Maint ainability Symposium (RAMS), IEEE

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.686316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 18d6b38b-1fd9-4f4c-83c8-b394fcfc8d32 · outbound

This paper cites Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA.

Attack and defense techniques in large language models: A survey and new perspectives Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-16T04:33:07.098165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 00910e95-d765-4646-bb3e-f1011d0eb765 · outbound

This paper cites Feature selection and d imension- ality reduction: An extensive comparison in hand gesture cl assiﬁca- tion by semg in eight channels armband approach.

Attack and defense techniques in large language models: A survey and new perspectives Feature selection and d imension- ality reduction: An extensive comparison in hand gesture cl assiﬁca- tion by semg in eight channels armband approach

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.662087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c3f66716-35c7-4196-9d69-705d4caa622c · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.673634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d528dbb-f9ba-4806-aad4-588db9aeaaf9 · outbound

This paper cites Common metadata framework: Int e- grated framework for trustworthy ai pipelines.

Attack and defense techniques in large language models: A survey and new perspectives Common metadata framework: Int e- grated framework for trustworthy ai pipelines

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.624807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d1c9a31-987b-4e01-81ef-22933583d5cd · outbound

This paper cites Thieves on Sesame Street! Model Extraction of BERT-based APIs.

Attack and defense techniques in large language models: A survey and new perspectives Thieves on Sesame Street! Model Extraction of BERT-based APIs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.304205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba5e84b-4e1c-4502-b538-18e1ce27e258 · outbound

This paper cites A syntactic analysis of the sentence structure in motivational quotes u sing tree diagram for english learning.

Attack and defense techniques in large language models: A survey and new perspectives A syntactic analysis of the sentence structure in motivational quotes u sing tree diagram for english learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.612540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 73d70622-7b9b-45ce-bb2c-78e59683c296 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.649714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0557c7d6-23ba-4104-81f8-b20208b68f40 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.636422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation befa2a7a-53cd-41c1-becd-17c5b6bcbdda · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.599489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8597a3ea-2a46-4069-958b-11ec07b4931f · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Attack and defense techniques in large language models: A survey and new perspectives DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.328044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e69b909-4b90-43a4-b48f-d95eb8043776 · outbound

This paper cites LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.331926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a89f46-1cc0-4c3f-b9f5-3358b5886cde · outbound

This paper cites Vocabulary attack to hij ack large lan- guage model applications.

Attack and defense techniques in large language models: A survey and new perspectives Vocabulary attack to hij ack large lan- guage model applications

Reference 35

Resolution: verified exact; raw_fallback, observed 2026-08-16T04:33:07.067821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 633717d6-8800-4008-8306-e706709a39f1 · outbound

This paper cites Privacy in Large Language Models: Attacks, Defenses and Future Directions.

Attack and defense techniques in large language models: A survey and new perspectives Privacy in Large Language Models: Attacks, Defenses and Future Directions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.316131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d186fb6-8200-403b-9875-2475bfd5dcd9 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.348294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10fb19f5-75cb-49de-a0c2-098fc5a2c72b · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.323833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2c1e36-a5e9-4f52-9525-64d45a70e3d0 · outbound

This paper cites Jailbreaking chatgpt vi a prompt engineering: An empirical study.

Attack and defense techniques in large language models: A survey and new perspectives Jailbreaking chatgpt vi a prompt engineering: An empirical study

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.562631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eaf8cbaa-bcfa-4522-8f51-5d3fc5776916 · outbound

This paper cites Summary of chatgpt-related re search and perspective towards the future of large language models.

Attack and defense techniques in large language models: A survey and new perspectives Summary of chatgpt-related re search and perspective towards the future of large language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.550976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 967d9a17-07b0-4ddf-9833-ee074c2ab3aa · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.586903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e95f2f02-4f72-4e60-acd5-c4b64c54d00d · outbound

This paper cites Dee p learning- based anomaly detection in cyber-physical systems: Progre ss and op- portunities.

Attack and defense techniques in large language models: A survey and new perspectives Dee p learning- based anomaly detection in cyber-physical systems: Progre ss and op- portunities

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.528534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 39dafa90-7602-4ab3-9cd0-9f408d55717e · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.344077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8442e6d-b6d3-452d-bd07-3f60178b30d3 · outbound

This paper cites Robust ac- tive learning (roal): Countering dynamic adversaries in ac tive learn- ing with elastic weight consolidation.

Attack and defense techniques in large language models: A survey and new perspectives Robust ac- tive learning (roal): Countering dynamic adversaries in ac tive learn- ing with elastic weight consolidation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.495495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6c2aceea-23bd-43df-905d-8a958a50343b · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Attack and defense techniques in large language models: A survey and new perspectives Prompt Injection attack against LLM-integrated Applications

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.352277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbeb2873-820d-4c89-9c5d-7e128806de4d · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.483846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2e860f1-0cc3-4a6a-9f45-4c6a9ff1f862 · outbound

This paper cites Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark.

Attack and defense techniques in large language models: A survey and new perspectives Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.390831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e266bb-3a41-4352-aac2-335577e6d0b1 · outbound

This paper cites Fo rmalizing and benchmarking prompt injection attacks and defenses, in : 33rd USENIX Security Symposium (USENIX Security 24), pp.

Attack and defense techniques in large language models: A survey and new perspectives Fo rmalizing and benchmarking prompt injection attacks and defenses, in : 33rd USENIX Security Symposium (USENIX Security 24), pp

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.539315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3b12c9ec-57b9-4d16-9773-67418b987550 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Attack and defense techniques in large language models: A survey and new perspectives SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.398286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6147760-08e1-4506-b602-f8f995a4aec6 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.517393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 827fb7ca-133b-43d8-93bd-04f8374d2d69 · outbound

This paper cites IEEE Communications Magazine.

Attack and defense techniques in large language models: A survey and new perspectives IEEE Communications Magazine

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.506779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4e743713-326e-4aca-9eb0-3e147fa2272b · outbound

This paper cites SPML: A DSL for Defending Language Models Against Prompt Attacks.

Attack and defense techniques in large language models: A survey and new perspectives SPML: A DSL for Defending Language Models Against Prompt Attacks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.413648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6c02df9-1107-4b23-a82d-64c72bee3aa1 · outbound

This paper cites ModelShield: Adaptive and Robust Watermark against Model Extraction Attack.

Attack and defense techniques in large language models: A survey and new perspectives ModelShield: Adaptive and Robust Watermark against Model Extraction Attack

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.383103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d92ab055-67fd-4b3c-9b16-c83d99e34c7d · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.438776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 08efc195-fe9c-4484-aa7d-9d7ee2124bd9 · outbound

This paper cites Signed-prompt: A new approach to prevent prompt Y.

Attack and defense techniques in large language models: A survey and new perspectives Signed-prompt: A new approach to prevent prompt Y

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.412531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f40a670f-8d49-40c1-a4e8-5bb8323b1892 · outbound

This paper cites Ignore previous prompt: A ttack tech- niques for language models.

Attack and defense techniques in large language models: A survey and new perspectives Ignore previous prompt: A ttack tech- niques for language models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.472659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f64e81e3-8ce4-4720-ad58-6faeb1e15a21 · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

Attack and defense techniques in large language models: A survey and new perspectives Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.546327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94232411-c09c-43c5-a0c4-dd62e82ac6cc · outbound

This paper cites An Early Categorization of Prompt Injection Attacks on Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives An Early Categorization of Prompt Injection Attacks on Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.402423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0d59d46-4494-42b7-9ef3-baec195da866 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.461608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c1a93b0-6d91-43b2-8b7d-fa717d7cd59e · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.450893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1e2bbd07-f08a-4e9b-83ce-dc02a4e62314 · outbound

This paper cites Selfdefend: Llms can defend themselves against jailbreaking in a practical manner.

Attack and defense techniques in large language models: A survey and new perspectives Selfdefend: Llms can defend themselves against jailbreaking in a practical manner

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.377445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f721ed67-26a5-41c3-b3ac-29d3ff93dab9 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

Attack and defense techniques in large language models: A survey and new perspectives Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.417707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96e205b-6428-4536-9398-469f8946115e · outbound

This paper cites Jailbro ken: How does llm safety training fail? Advances in Neural Information Pr ocessing Systems 36, 80079–80110.

Attack and defense techniques in large language models: A survey and new perspectives Jailbro ken: How does llm safety training fail? Advances in Neural Information Pr ocessing Systems 36, 80079–80110

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.341799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b66060d9-27ed-4b11-a3d7-167291a1a766 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.425907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 198e8267-efac-4575-ba90-0152e94eac2f · outbound

This paper cites Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts.

Attack and defense techniques in large language models: A survey and new perspectives Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.581334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9fb5e5a-1564-4fc1-8bd5-9013feeb2ac7 · outbound

This paper cites Meta-learning appr oaches for learning-to-learn in deep learning: A survey.

Attack and defense techniques in large language models: A survey and new perspectives Meta-learning appr oaches for learning-to-learn in deep learning: A survey

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.400843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 61817e8a-8040-48b7-9232-69bc1a83c62c · outbound

This paper cites GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis.

Attack and defense techniques in large language models: A survey and new perspectives GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.588648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c46fe94-1233-46ab-9742-2b8943c081db · outbound

This paper cites Imitation Attacks and Defenses for Black-box Machine Translation Systems.

Attack and defense techniques in large language models: A survey and new perspectives Imitation Attacks and Defenses for Black-box Machine Translation Systems

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-08-16T04:33:06.815448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 552e3aae-d3ef-4ef2-ac81-0986ab334d73 · outbound

This paper cites Adversarial Demonstration Attacks on Large Language Models.

Attack and defense techniques in large language models: A survey and new perspectives Adversarial Demonstration Attacks on Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.554430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd08f14a-4a63-4bf1-927d-647bb7f4b3be · outbound

This paper cites A multiobje ctive learn- ing and ensembling approach to high-performance speech enh ance- ment with compact neural network architectures.

Attack and defense techniques in large language models: A survey and new perspectives A multiobje ctive learn- ing and ensembling approach to high-performance speech enh ance- ment with compact neural network architectures

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.389147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5ff8918c-7b5a-4bd7-a687-0a0642c7e721 · outbound

This paper cites PRSA: Prompt Stealing Attacks against Real-World Prompt Services.

Attack and defense techniques in large language models: A survey and new perspectives PRSA: Prompt Stealing Attacks against Real-World Prompt Services

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.606888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b32a7f3-8149-4f5e-a174-d41f43e3d073 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.365493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 52bc5694-e826-424c-8a44-153e8f8b106a · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Attack and defense techniques in large language models: A survey and new perspectives GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.614789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d318c2-9be3-4d71-b8c6-4901eb006cb9 · outbound

This paper cites Assessing Prompt Injection Risks in 200+ Custom GPTs.

Attack and defense techniques in large language models: A survey and new perspectives Assessing Prompt Injection Risks in 200+ Custom GPTs

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.618480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cd12cf8-ef86-4a7c-b00c-6289a1ee42e6 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Attack and defense techniques in large language models: A survey and new perspectives Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.577405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cb6eeed-9865-4377-a9a8-48d40f44dc71 · outbound

This paper cites Gener ate adversar- ial examples by adaptive moment iterative fast gradient sig n method.

Attack and defense techniques in large language models: A survey and new perspectives Gener ate adversar- ial examples by adaptive moment iterative fast gradient sig n method

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.267398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99fe5dd2-8c1a-48c5-bc71-3a11a9ff58f3 · outbound

This paper cites Distract Large Language Models for Automatic Jailbreak Attack.

Attack and defense techniques in large language models: A survey and new perspectives Distract Large Language Models for Automatic Jailbreak Attack

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.585083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf56bac-71ae-4d3f-a8b1-21c1c05e3c92 · outbound

This paper cites Anomaly detection wit h robust deep autoencoders, in: Proceedings of the 23rd ACM SIGKDD in - ternational conference on knowledge discovery and data min ing, pp.

Attack and defense techniques in large language models: A survey and new perspectives Anomaly detection wit h robust deep autoencoders, in: Proceedings of the 23rd ACM SIGKDD in - ternational conference on knowledge discovery and data min ing, pp

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.242272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation edd64977-826f-4de4-b602-58e2a8129c93 · outbound

This paper cites an unresolved cited work.

Attack and defense techniques in large language models: A survey and new perspectives Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:33:07.329235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 77cd5880-92c3-4557-9f96-a67fa6710e69 · outbound

This paper cites Nature Machine Intelligence 5, 1486–1496.

Attack and defense techniques in large language models: A survey and new perspectives Nature Machine Intelligence 5, 1486–1496

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.317903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f7753098-8a0b-4b0f-b287-894aac59259f · outbound

This paper cites Practical and ethical cha llenges of large language models in education: A systematic scoping review.

Attack and defense techniques in large language models: A survey and new perspectives Practical and ethical cha llenges of large language models in education: A systematic scoping review

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.306011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55e84324-706e-4116-a7db-01138fca41ac · outbound

This paper cites Harnessing the power of llms in practi ce: A survey on chatgpt and beyond.

Attack and defense techniques in large language models: A survey and new perspectives Harnessing the power of llms in practi ce: A survey on chatgpt and beyond

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.292848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9760144-526a-41ed-9fa2-a78c24e6ccdc · outbound

This paper cites Poisonprompt: Backdoor attack on prompt-based large language models, in: ICASSP 2024-2024 I EEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.

Attack and defense techniques in large language models: A survey and new perspectives Poisonprompt: Backdoor attack on prompt-based large language models, in: ICASSP 2024-2024 I EEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.279947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c252686f-dd82-4de3-9377-8ba484070689 · outbound

This paper cites AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.

Attack and defense techniques in large language models: A survey and new perspectives AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.622439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc31aad5-7740-4fb6-a81f-cf9d4fb56182 · outbound

This paper cites Protecting language generation models via invisible watermarking, in: International Conf erence on Machine Learning, PMLR.

Attack and defense techniques in large language models: A survey and new perspectives Protecting language generation models via invisible watermarking, in: International Conf erence on Machine Learning, PMLR

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.254974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2bed685-b5a7-406b-ab66-71fb157f5c9c · outbound

This paper cites Risks of discrimination violence and un lawful actions in llm-driven robots.

Attack and defense techniques in large language models: A survey and new perspectives Risks of discrimination violence and un lawful actions in llm-driven robots

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.227799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b75629ad-6076-4a30-8f69-f34a44dc48d2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Attack and defense techniques in large language models: A survey and new perspectives Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.641038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e018281-8599-4447-8c42-15e71a133fd2 · outbound

This paper cites Proceedin gs of the IEEE 108, 2214–2231.

Attack and defense techniques in large language models: A survey and new perspectives Proceedin gs of the IEEE 108, 2214–2231

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.573818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation aa99a021-045a-488a-b1c4-de3c76349811 · outbound

This paper cites 2633– 2650.

Attack and defense techniques in large language models: A survey and new perspectives 2633– 2650

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.207280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f3387d-9471-450a-bd5f-56e8a4f66e47 · outbound

This paper cites 10379– 10388.

Attack and defense techniques in large language models: A survey and new perspectives 10379– 10388

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:33:07.353654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e22a8fd0-2dae-4e0e-8a66-f79dd5ab2521 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Attack and defense techniques in large language models: A survey and new perspectives Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.282306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9002336-a86f-4ffa-942f-1c6bcbdc8216 · outbound

This paper cites arXiv preprint arXiv:240 4.16251.

Attack and defense techniques in large language models: A survey and new perspectives arXiv preprint arXiv:240 4.16251

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T04:33:06.187461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 46285b36-c596-4a1f-bac7-0bbd1f43205f · inbound

Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations cites this paper.

Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations Attack and defense techniques in large language models: A survey and new perspectives

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T11:23:45.644623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6b9ebca-6a6d-4ce6-9722-41a2bcb1cf77 · inbound

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts cites this paper.

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts Attack and defense techniques in large language models: A survey and new perspectives

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T04:25:52.253069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9433373-0fc3-4415-a886-ea90cb838d70 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Attack and defense techniques in large language models: A survey and new perspectives

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.747757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 719c31f6-d905-4328-935f-7bbfebbafa4a · inbound

Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout cites this paper.

Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout Attack and defense techniques in large language models: A survey and new perspectives

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:51:10.957370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b8d58460-56ee-4a31-abdf-8c3a106993fd · inbound

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing cites this paper.

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing Attack and defense techniques in large language models: A survey and new perspectives

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T09:08:26.246230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b45ec352-e572-4bcf-abc0-7b9131838e10 · inbound

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models cites this paper.

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models Attack and defense techniques in large language models: A survey and new perspectives

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T14:21:42.232920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.