Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-15T20:12:28.410564Z
Paper Citation Record · LEDGER
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
As of 20 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 5 inbound Pith citation observations for arXiv:2505.13862.
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 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T10:17:26.916448Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-18T18:56:45.840997Z
Reference resolution
68 of 68 outbound references displayed
- verified exact1
- verified fuzzy26
- unresolved41
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation df60a4c9-065c-486b-b7ac-20e5933b61f6 · outbound
This paper cites Language models are few-shot learners.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Language models are few-shot learners
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:27.952093Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 28de3028-cefa-44eb-a708-5c9bdebaed77 · outbound
This paper cites The Llama 3 Herd of Models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks The Llama 3 Herd of Models
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:27.959029Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f0b7cbf-1b15-42e9-a6eb-4ac51fec35f0 · outbound
This paper cites Qwen2.5 Technical Report.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Qwen2.5 Technical Report
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:27.965475Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f42d85c6-a069-494e-8907-c733c42ba4ff · outbound
This paper cites Gemini - Our most intelligent AI models, built for the agentic era, 2025.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Gemini - Our most intelligent AI models, built for the agentic era, 2025
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.939360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation aa19e645-c592-4fb8-972f-6a658926bac0 · outbound
This paper cites Eureka: Human-level reward design via coding large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Eureka: Human-level reward design via coding large language models
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.918845Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 40ca29c7-6ba4-4278-b073-8077625fdc2a · outbound
This paper cites Creating large language model applications utilizing langchain: A primer on developing llm apps fast.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Creating large language model applications utilizing langchain: A primer on developing llm apps fast
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.896603Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9c09b8a8-f03c-48d4-9b3d-966ea09ffdb0 · outbound
This paper cites Taxonomy of risks posed by language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Taxonomy of risks posed by language models
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:27.996184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef1706d5-da10-47fd-9963-bdbcc9a7ebc2 · outbound
This paper cites Navigating the risks: A review of safety issues in large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Navigating the risks: A review of safety issues in large language models
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.850221Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation b0bf3749-b52a-4709-a08e-d22973a5053b · outbound
This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks A survey on large language model (llm) security and privacy: The good, the bad, and the ugly
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.010548Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c117881-0b0c-4e9c-b21b-0b863a6aba2e · outbound
This paper cites Multimodal situational safety.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Multimodal situational safety
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.809951Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation dba124c1-07b9-45af-b6f2-d440207e5696 · outbound
This paper cites Air-bench 2024: A safety benchmark based on regulation and policies specified risk categories.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Air-bench 2024: A safety benchmark based on regulation and policies specified risk categories
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.784390Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d19f4f79-0f54-4a4d-af8d-e4fa17fd46f8 · outbound
This paper cites Safe rlhf: Safe reinforcement learning from human feedback.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Safe rlhf: Safe reinforcement learning from human feedback
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.030062Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 62005d79-be73-4562-bb62-37f732cd1b2b · outbound
This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.036730Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 117632e5-4bce-4502-8524-66f8ac717635 · outbound
This paper cites Zico Kolter, and Matt Fredrikson.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Zico Kolter, and Matt Fredrikson
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.044177Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fbf680e-e989-4c37-a0fd-9894f09cb4d1 · outbound
This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.050206Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 547b3c93-8e26-4c08-98c5-34219cd2557d · outbound
This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreak Attacks and Defenses Against Large Language Models: A Survey
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.056212Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce3c3ccf-2d06-49e5-ac7c-7cf0b2153678 · outbound
This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.062971Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f91d558-0aab-4c3f-9204-a0809c379448 · outbound
This paper cites Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.070723Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ca58e9ef-186d-4163-a9bd-0937d8001d7b · outbound
This paper cites Jailbreak antidote: Runtime safety-utility balance via sparse representation adjustment in large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreak antidote: Runtime safety-utility balance via sparse representation adjustment in large language models
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.732854Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4e7c375d-e4b4-4c32-af61-51fd5b2a7bee · outbound
This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Autodan: Generating stealthy jailbreak prompts on aligned large language models
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.081961Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e23ca5eb-8e7b-4054-8846-bb347eec362d · outbound
This paper cites Jailbreaking black box large language models in twenty queries.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreaking black box large language models in twenty queries
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.683140Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 92d0f952-ef6e-45ba-93d5-a2caea2fa3a1 · outbound
This paper cites Defending chatgpt against jailbreak attack via self-reminders.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Defending chatgpt against jailbreak attack via self-reminders
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.092938Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6f6b1eee-5318-46c1-bc88-0e3174ba4240 · outbound
This paper cites Defending llms against jailbreak- ing attacks via backtranslation.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Defending llms against jailbreak- ing attacks via backtranslation
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.638761Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4b7e79ab-22a6-4ca3-8149-57b07f1f491b · outbound
This paper cites Pku-saferlhf: A safety alignment preference dataset for llama family models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Pku-saferlhf: A safety alignment preference dataset for llama family models
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.494475Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fb551892-74a7-40f4-a74b-9679ca250279 · outbound
This paper cites AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.109825Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cc9e03ed-3170-4be0-ac20-a66274b48ff8 · outbound
This paper cites Bag of tricks: Benchmarking of jailbreak attacks on llms.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Bag of tricks: Benchmarking of jailbreak attacks on llms
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.473277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 36bdcb7e-004a-4ee3-9615-466a71a03cb8 · outbound
This paper cites Safetybench: Evaluating the safety of large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Safetybench: Evaluating the safety of large language models
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.122027Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 525f3b0b-d83b-410f-82f1-d5b88db63591 · outbound
This paper cites Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.128237Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 11714a50-da6d-4253-aeef-d85e5da45f71 · outbound
This paper cites A survey on evaluation of large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks A survey on evaluation of large language models
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.134188Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4f293da4-244d-4fd7-b960-c705317b1ba7 · outbound
This paper cites Advbench: a framework to evaluate adversarial attacks against fraud detection systems.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Advbench: a framework to evaluate adversarial attacks against fraud detection systems
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.400243Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ee761edf-f374-4537-aaf6-1bd7323fdb57 · outbound
This paper cites Jailjudge: A comprehensive jailbreak judge benchmark with multi-agent enhanced explanation evaluation framework, 2024.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailjudge: A comprehensive jailbreak judge benchmark with multi-agent enhanced explanation evaluation framework, 2024
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.374479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9c2a1e22-bd67-42b2-8a68-d268c8b5f526 · outbound
This paper cites EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.154029Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d86aa3a-948e-4ef6-ab23-a8f3fcd2b301 · outbound
This paper cites Harmbench: a standardized evaluation frame- work for automated red teaming and robust refusal.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Harmbench: a standardized evaluation frame- work for automated red teaming and robust refusal
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.348580Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7b881c55-f619-4f66-83f6-45e58a27cd2f · outbound
This paper cites Gonzalez, Hao Zhang, and Ion Stoica.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Gonzalez, Hao Zhang, and Ion Stoica
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.166852Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e428f175-7e1f-42cc-9850-57c51c630ac7 · outbound
This paper cites Sglang: Efficient execution of structured language model programs.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Sglang: Efficient execution of structured language model programs
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.174978Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 108b9efa-00dd-481b-9b4a-6ff18aa6a91d · outbound
This paper cites Ollama: Run large language models locally, 2025.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Ollama: Run large language models locally, 2025
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.292654Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e508776e-ec90-43ec-8240-6c0c65e10bd4 · outbound
This paper cites Jailbreak chat.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreak chat
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.271428Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 1cbf9e98-4525-4e5b-acc8-d1f2c5e070f8 · outbound
This paper cites Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.199798Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b641bc0-a644-4e23-a30f-4ecfbe748f13 · outbound
This paper cites Improved generation of adversarial examples against safety-aligned LLMs.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Improved generation of adversarial examples against safety-aligned LLMs
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.237976Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ee501cbe-1cb2-4f4b-8565-f22cad340991 · outbound
This paper cites Jailbreaking leading safety-aligned llms with simple adaptive attacks.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreaking leading safety-aligned llms with simple adaptive attacks
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.217084Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9d093622-b3b9-4573-9b87-a1c59e925046 · outbound
This paper cites Does refusal training in llms generalize to the past tense? In Neurips Safe Generative AI Workshop 2024, 2024.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Does refusal training in llms generalize to the past tense? In Neurips Safe Generative AI Workshop 2024, 2024
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.192233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 0b6db335-661d-4f74-983b-e9d420caf9d2 · outbound
This paper cites Rain- bow teaming: Open-ended generation of diverse adversarial prompts.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Rain- bow teaming: Open-ended generation of diverse adversarial prompts
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.170330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation be8f0d35-a25a-4e36-895f-1e646b4e2338 · outbound
This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Artprompt: Ascii art-based jailbreak attacks against aligned llms
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.237023Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06ebc475-7517-4d1d-93eb-36acfae75382 · outbound
This paper cites Deepinception: Hypnotize large language model to be jailbreaker.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Deepinception: Hypnotize large language model to be jailbreaker
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.245128Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70f47f65-b2bc-4457-a4d7-dd3004d128e7 · outbound
This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.252253Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 74d3bf7e-424f-4930-ade8-9dc28e009b55 · outbound
This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.259897Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c883163e-e2d2-42b8-a865-f62e33ce04dd · outbound
This paper cites Defending large language models against jailbreaking attacks through goal prioritization.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Defending large language models against jailbreaking attacks through goal prioritization
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.117089Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 80a7c5a8-b76a-4556-b50e-fb10ebe7720f · outbound
This paper cites Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.274891Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e51d652-fb1b-4145-b576-ded5c0ed92b7 · outbound
This paper cites Llm self defense: By self examination, llms know they are being tricked.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Llm self defense: By self examination, llms know they are being tricked
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.284370Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb67fe54-6dba-4199-8a35-df3e5318e44d · outbound
This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Representation Engineering: A Top-Down Approach to AI Transparency
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.291761Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbd7e63d-23be-480e-840e-cbdd99a7fb7d · outbound
This paper cites Safe lora: The silver lining of reducing safety risks when finetuning large language models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Safe lora: The silver lining of reducing safety risks when finetuning large language models
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:29.079297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7fc3552a-a6a5-4bda-af0b-c20fc3a9c00f · outbound
This paper cites Training language models to follow instructions with human feedback.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Training language models to follow instructions with human feedback
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.306823Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6162b60d-3417-4222-a562-470ec91211a5 · outbound
This paper cites Direct preference optimization: Your language model is secretly a reward model.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Direct preference optimization: Your language model is secretly a reward model
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.312870Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44affa0e-f407-49f7-8e20-c38b7e980fae · outbound
This paper cites Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.318309Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f21669cd-3664-4567-9a4c-51c89bbd2c93 · outbound
This paper cites A Survey on LLM-as-a-Judge.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks A Survey on LLM-as-a-Judge
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.324184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa8787ee-838d-4920-b296-e9212cf735a3 · outbound
This paper cites Promptbench: Towards evaluating the robustness of large language models on adversarial prompts.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Promptbench: Towards evaluating the robustness of large language models on adversarial prompts
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.330644Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f3c5e57-b04f-4365-88e2-b767847464de · outbound
This paper cites Decodingtrust: A comprehensive assessment of trustworthiness in gpt models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Decodingtrust: A comprehensive assessment of trustworthiness in gpt models
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.337667Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cac776c4-a048-4bac-8563-ec5817bec7ea · outbound
This paper cites TrustLLM: Trustworthiness in Large Language Models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks TrustLLM: Trustworthiness in Large Language Models
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.343741Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 19a5bcf9-4c1b-4e99-a5ca-c75c08940efd · outbound
This paper cites an unresolved cited work.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-08-15T20:12:29.006340Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7c3bf811-89c5-4df6-8959-ad73037762fb · outbound
This paper cites an unresolved cited work.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Unresolved cited work
Reference 60
- Resolution
- unresolved
- raw_fallback, observed 2026-08-15T20:12:28.984753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7c66d790-b8c7-4409-899b-0c6e8fb680c0 · outbound
This paper cites Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105, 2024.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105, 2024
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.362060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4b203de0-b6f9-4db1-bdb6-cbd4ac463b61 · outbound
This paper cites Hashimoto.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Hashimoto
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.368265Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 195e4141-5804-4e75-9cdd-497e0384c223 · outbound
This paper cites Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:28.933483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2cb7c7aa-8f91-49a8-bb57-79e5a3691a0e · outbound
This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
Reference 64
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T20:12:28.380405Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cc13dcd-540d-4f6c-b618-b4ee84c85a78 · outbound
This paper cites Uncovering safety risks of large language models through concept activation vector.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Uncovering safety risks of large language models through concept activation vector
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:28.908294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 16ad5843-ad03-4cde-ae97-7ec4da586707 · outbound
This paper cites Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
Reference 66
- Resolution
- verified exact
- local_arxiv, observed 2026-08-15T20:12:28.483228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 8e03b60a-4202-4add-b3a5-d5e50da0d3a5 · outbound
This paper cites Robust prompt optimization for defending language mod- els against jailbreaking attacks.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks Robust prompt optimization for defending language mod- els against jailbreaking attacks
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:28.885088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation b1701f1d-7cba-4dae-8844-f7f053c1c0dc · outbound
This paper cites I’m sorry.
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks I’m sorry
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T20:12:28.865944Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Pith citing papers
Observation 1f4f6028-cdad-4fcd-9f77-f3ac8d3676a6 · inbound
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs cites this paper.
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Reference 106
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T10:17:26.916448Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bbdcf00c-f351-4fe0-8dbd-a1677a965279 · inbound
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal cites this paper.
Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T18:56:45.844559Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c0a14eb1-5771-4397-bd1c-340f8a782158 · inbound
Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks cites this paper.
Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T09:40:46.486872Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bc2eb868-8ecd-46a3-9d65-9f2663b84adc · inbound
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models cites this paper.
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T20:23:23.520526Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 65b758ab-7aa9-48e5-8e67-aff1f084d2d1 · inbound
SoK: Robustness in Large Language Models against Jailbreak Attacks cites this paper.
SoK: Robustness in Large Language Models against Jailbreak Attacks PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Reference 71
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T18:01:08.732256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.