Paper Citation Record · LEDGER

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2402.08679.

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

pith.paper-citation-record.v1
2402.08679 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:35:21.278845Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T19:50:11.145122Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 7dc8bf30-aa44-492d-ab4e-2afbfcc5b876 · inbound

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment cites this paper.

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-24T00:38:39.981082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a7c2b66-937a-4345-9359-9e19c5744a60 · inbound

Jailbreak Attacks and Defenses Against Large Language Models: A Survey cites this paper.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:20:44.649287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 03979045-6da7-4365-8526-870ccb24d34f · inbound

Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics cites this paper.

Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T22:32:12.954917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a053897b-589c-4975-b2ea-f27e28840223 · inbound

Adversarial Preference Learning for Robust LLM Alignment cites this paper.

Adversarial Preference Learning for Robust LLM Alignment COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:21.278845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 644770f6-f978-49a1-8c07-841eeb5244af · inbound

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models cites this paper.

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:51:31.581115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eba21bb8-2c2f-4933-94eb-e0b8a11402c2 · inbound

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks cites this paper.

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:24.189376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdc94e7-169b-41ab-9e61-63d88ead5892 · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.641819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d6e4e7d-f0d4-495d-8c1f-029d5b7109fa · inbound

Adaptive Content Restriction for Large Language Models via Suffix Optimization cites this paper.

Adaptive Content Restriction for Large Language Models via Suffix Optimization COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:58.325167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512e92fe-7ea0-4a83-b1d9-7f13210766df · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.972622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b74580c-e5aa-4de2-af2b-41a82de52755 · inbound

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives cites this paper.

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-05T18:12:37.189913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 959cbe90-79e5-444a-8150-c924af79b856 · inbound

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring cites this paper.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.667508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a676b136-449c-4440-adec-2f98c854da4e · inbound

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint cites this paper.

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T23:10:21.277726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ba4a17-9d7e-4a19-8b37-598ca4bf46c7 · inbound

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security cites this paper.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.515431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebe02e7b-4f76-4c39-9cb4-dfe6e23130b8 · 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 COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:00:06.471703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d38698-e6f3-47cf-ac97-c5cf118cb558 · inbound

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization cites this paper.

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T11:11:00.443361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc655edd-f014-4170-8710-fc4be3fffd6c · inbound

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs cites this paper.

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:55:38.107722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 88091f53-7646-4091-8521-989e081c4e5d · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:20:57.972169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6deb68e8-9e7b-40f3-829f-7af9ddd7628f · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T16:34:03.945251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d6ff13-23c9-4655-b541-6420a6a35a67 · inbound

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs cites this paper.

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:26:00.029979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 58685fd8-51ec-40fa-9dfe-3bc632cd8a88 · inbound

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming cites this paper.

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-10T03:08:59.273795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3c824040-4556-4982-a3f0-9912bdecf8c6 · inbound

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models cites this paper.

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T04:49:35.496621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 16e4472a-7f36-48ee-af6e-cbe5c49b9e8f · inbound

Adversarial Reframing: A Framework for Targeted Generation in Language Models cites this paper.

Adversarial Reframing: A Framework for Targeted Generation in Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:36:20.994701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 462a2daf-22b4-43cf-a9c8-9acf5948e827 · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-07-04T19:50:11.146715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f687973f-0d21-459e-9f29-1292a72ed43f · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T10:16:41.626900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cbd144b-cd6e-40b6-b065-7c8fe71ab14c · inbound

One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models cites this paper.

One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T21:01:04.881568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e76c0b05-541f-4199-9896-e5336725ddf1 · inbound

Weak-to-Strong On-Policy Distillation cites this paper.

Weak-to-Strong On-Policy Distillation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T00:26:21.232534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a536787a-3a5f-4751-9dba-ec9f93c6c34d · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:39.746628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.