Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations | Paper Citation Record

Observation 117d23d0-55a9-4849-8078-a4f74db8fd9c · inbound

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

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:20:44.426486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6381b773-e8c9-48c4-92ef-f99986a5ad55 · inbound

DROJ: A Prompt-Driven Attack against Large Language Models cites this paper.

DROJ: A Prompt-Driven Attack against Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T21:05:18.300047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ca19ab0-3dea-4262-820a-f10d6891b276 · inbound

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization cites this paper.

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T18:41:06.153149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c95fb98b-469c-4d12-a165-66b54dc5fc35 · inbound

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM cites this paper.

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T18:53:15.305158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fedc0ca-9974-49fb-8a0f-8024c1a93efe · inbound

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning cites this paper.

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T15:49:38.142015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d24f0f6a-2382-49ba-b029-bfaf1f3e4515 · inbound

Towards Responsible Governing AI Proliferation cites this paper.

Towards Responsible Governing AI Proliferation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-11T12:47:48.601255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cfd5c5e-551a-4de1-8066-5a1b12d2d127 · inbound

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models cites this paper.

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:26.713244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc1274f-7c2e-475b-99c0-af3b7e4c34ac · inbound

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models cites this paper.

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T23:40:38.873180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ef6edf3-7144-427a-8a56-67f480a69451 · inbound

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation cites this paper.

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T22:28:56.732300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 962b564d-6ac9-41c1-8db9-b5cc36a03762 · inbound

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models cites this paper.

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T22:25:54.723257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ef1e05-0fd2-4d45-bd4d-a8d6458c5f61 · inbound

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs cites this paper.

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T22:35:26.984854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d605eed-3151-4592-a9e4-07be3a451d65 · inbound

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense cites this paper.

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T22:11:59.912758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed581a41-2e19-4c3a-93a0-50d01a279b19 · inbound

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning cites this paper.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.856473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19cf3e0d-9de7-48fe-b988-f87b47517819 · inbound

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks cites this paper.

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T19:08:01.737120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb412c3f-1d20-49c5-8853-766be59699f9 · inbound

Episodic memory in AI agents poses risks that should be studied and mitigated cites this paper.

Episodic memory in AI agents poses risks that should be studied and mitigated Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-10T17:58:18.112923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0175743d-88fe-4eb6-9851-69008c436cdf · inbound

PromptShield: Deployable Detection for Prompt Injection Attacks cites this paper.

PromptShield: Deployable Detection for Prompt Injection Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:38:10.811952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f26dd78-4c35-4556-8f79-98f7892de47d · inbound

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models cites this paper.

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T00:12:04.817181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a928bc4c-1dd2-43bd-862a-186b3966b4c8 · inbound

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling cites this paper.

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T14:02:38.908552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e184b199-3148-4634-bc49-02b558a134dc · inbound

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation cites this paper.

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T12:25:30.673565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2a488f1-08c4-43a6-a2a4-94b88f78a080 · inbound

MetaSC: Test-Time Safety Specification Optimization for Language Models cites this paper.

MetaSC: Test-Time Safety Specification Optimization for Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T11:15:45.010325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d0bbf9-03d8-49cd-8153-bb7f999c5e68 · inbound

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification cites this paper.

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T12:10:31.064804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecf5f09d-1fdf-4ef4-912b-9a0129a3c8ff · inbound

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control cites this paper.

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:52:07.409816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a0912ed-9faf-4177-80bf-8c2623f7a839 · inbound

The Automation Advantage in AI Red Teaming cites this paper.

The Automation Advantage in AI Red Teaming Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T05:46:02.176124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

Attack and defense techniques in large language models: A survey and new perspectives cites this paper.

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 f2908be1-0bdb-4385-8425-46098b195243 · inbound

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement cites this paper.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.311556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb7c7aa-8f91-49a8-bb57-79e5a3691a0e · inbound

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks cites this paper.

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 cba2e2e6-8940-425b-aecc-e698ad06b693 · inbound

Advancing LLM Safe Alignment with Safety Representation Ranking cites this paper.

Advancing LLM Safe Alignment with Safety Representation Ranking Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.326956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdd8198-b371-4ea6-b84c-bdc93100f652 · inbound

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval cites this paper.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.745729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380184e7-86ed-4d1d-acad-bd528028193c · inbound

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models cites this paper.

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:41.028053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f79f5c5-dadf-42b5-871f-460fbc8e94b7 · inbound

Secure LLM Fine-Tuning via Safety-Aware Probing cites this paper.

Secure LLM Fine-Tuning via Safety-Aware Probing Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-22T13:11:35.853681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 50dc41cf-1536-4e7b-869a-64ad6d1d0615 · inbound

Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation cites this paper.

Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:32:30.720380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315c024d-59f5-4a55-8fe7-56370521a7b3 · inbound

Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts cites this paper.

Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T14:01:11.052058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73d2de4a-8bd0-44b0-b6e4-7b1dec2610c8 · inbound

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models cites this paper.

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:24.102566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5faeabe1-ec16-46fd-8fbe-ec8a76ffd52e · inbound

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap cites this paper.

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:22.236454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75792518-7d97-4fe7-917b-fcd454ccace3 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:37:15.987956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 60f67dd0-5532-4871-9215-078dcc65b23a · inbound

Adversarial Attacks on Robotic Vision Language Action Models cites this paper.

Adversarial Attacks on Robotic Vision Language Action Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T11:11:40.551096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd6921c-f91f-4c0e-b1af-47bf8baa381a · inbound

TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts cites this paper.

TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:58.135736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de60991d-b09f-4bc5-815e-e386c2095b22 · inbound

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations cites this paper.

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:57:16.542808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b255213c-9252-42fc-8015-5501bcc45f5a · inbound

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges cites this paper.

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:35:10.112904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bfa0aee-8356-4b43-a9f4-82adba2f8a86 · 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 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-07T10:17:27.001406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f36b96-93fa-4d92-8919-e1cc47c74088 · inbound

InfoFlood: Jailbreaking Large Language Models with Information Overload cites this paper.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.037588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ac8baf-a28d-404b-aed8-130ee71f471c · inbound

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem cites this paper.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.987996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d5aa00-3481-44ee-a5fb-50e0a81e5135 · inbound

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models cites this paper.

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T19:31:54.439019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd11a48-ed3f-4c4d-be94-32473105ddd4 · inbound

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models cites this paper.

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:20:53.797609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8564b34-057e-407c-bf81-6ed1135155b4 · inbound

Linearly Decoding Refused Knowledge in Aligned Language Models cites this paper.

Linearly Decoding Refused Knowledge in Aligned Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.014424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e12c66-942d-4f13-b196-686c4bf8756d · inbound

Defending Against Prompt Injection With a Few DefensiveTokens cites this paper.

Defending Against Prompt Injection With a Few DefensiveTokens Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:42.838856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78c43e03-bdbb-458f-83aa-5413134e33b9 · 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 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.743717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2e2b86-141e-493b-a58e-0e75f00be4e4 · inbound

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models cites this paper.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.100347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0d19bb1-5cea-4a7d-928b-271ecf66ead2 · inbound

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? cites this paper.

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:34.156403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 218856ef-8017-4313-b7d8-3c4288aa9d6f · inbound

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles cites this paper.

PUZZLED: Jailbreaking LLMs through Word-Based Puzzles Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:43:39.293986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53d180c-a509-4bc2-8d06-8efb4e8c110b · inbound

Automatic LLM Red Teaming cites this paper.

Automatic LLM Red Teaming Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 1685

Resolution: unresolved; no resolver link, observed 2026-08-06T00:04:25.504135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d2042c-6acd-4c2f-8ba3-21a2845c9a02 · inbound

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection cites this paper.

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T22:24:23.428703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bbdb906-2757-4b09-abf5-0001b09d1ebc · inbound

A Survey on Training-free Alignment of Large Language Models cites this paper.

A Survey on Training-free Alignment of Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-05T21:18:48.551115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e071d78-c297-4a80-8084-43d8cac74c4f · inbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.559678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9443b52e-49d8-4b5e-b54b-912e938cb6bd · inbound

Mitigating Jailbreaks with Intent-Aware LLMs cites this paper.

Mitigating Jailbreaks with Intent-Aware LLMs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.137872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2380904f-c806-4730-9838-7803ec4e6629 · inbound

CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection cites this paper.

CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T17:18:24.500459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103a5d3e-866c-42b7-a0b0-5c77d922d988 · inbound

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks cites this paper.

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T18:05:32.424178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe642ff8-1d94-4870-a75b-bc2df70e9cc0 · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:52.110346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921a1417-8384-499b-97e9-4bdae34b8f08 · inbound

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs cites this paper.

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:36:52.479691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 262a77df-7593-46d2-b169-d8fe64bae7d3 · inbound

Baichuan-M2: Scaling Medical Capability with Large Verifier System cites this paper.

Baichuan-M2: Scaling Medical Capability with Large Verifier System Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T11:50:14.742567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcf06fb2-f84c-486c-9e38-4c9f4c0ca189 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 264

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:08.207569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881ed3e0-8875-48cf-a485-a295d796bf27 · 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 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.470662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb991391-33fa-4d40-b1c4-1646f578c6a8 · inbound

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses cites this paper.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 200

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:57.778089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b9af65f-eef9-4e39-b148-2c7c4b2f4287 · inbound

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models cites this paper.

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-18T05:25:54.630924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5187e3f8-ddbc-49ef-b93f-23f7013e2313 · inbound

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.120540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e241d81d-697b-4658-86dc-2532dc2b8cd0 · 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 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:55:38.050506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1c861905-1bde-4f80-b222-a54f7756b3e8 · inbound

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents cites this paper.

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-25T07:05:26.677753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b6802b60-e140-435f-8723-813ea5ddc511 · inbound

ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files cites this paper.

ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.375753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b6f4ff22-d27a-4aa8-b762-1b9e0680ce30 · inbound

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense cites this paper.

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:35:50.778962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d58642f-7d0f-43f0-9c67-768094314bbb · inbound

GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking cites this paper.

GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-10T16:45:37.340698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 25c6cce4-a38e-4317-b3ab-66456ab89088 · 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 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:26:00.015367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7b10e68e-4c58-4538-949f-52ec49ce67bb · inbound

A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff cites this paper.

A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-12T20:09:57.922788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2448a1f-80b8-4bbe-b1be-faeaf618d404 · inbound

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection cites this paper.

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:35:18.931019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 75fea871-0b2c-455e-b68a-69d3a924bc36 · inbound

A Systematic Study of Training-Free Methods for Trustworthy Large Language Models cites this paper.

A Systematic Study of Training-Free Methods for Trustworthy Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:22:37.353269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c0804e6e-5974-4d59-9fc7-fcc348e25e30 · inbound

Jailbreaking Large Language Models with Morality Attacks cites this paper.

Jailbreaking Large Language Models with Morality Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:21:27.030426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 654cd810-3283-4979-be35-e00290ea9fe6 · inbound

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models cites this paper.

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:06:04.411354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c698fb39-f359-4ccf-bc76-66c16fef678f · inbound

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation cites this paper.

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:31:09.476633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 63e4218e-7582-4fa1-9f5b-30946ea95025 · inbound

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework cites this paper.

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:09.567702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5d7afb9e-d275-447f-9f23-c01aedbff02b · inbound

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models cites this paper.

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:01:09.629032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 598a05e0-a41c-42a9-858b-69653353566e · inbound

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms cites this paper.

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:51:43.987363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 833c9c08-b805-4c2d-828c-8bd4f095fd6c · inbound

PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures cites this paper.

PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-20T18:03:36.763330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c766b4e8-3c80-4acc-acc4-12cc8b8205e3 · inbound

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models cites this paper.

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:53:47.699039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 440422c9-2f00-4359-a058-80339a4cc457 · inbound

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models cites this paper.

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:46:19.173126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0806e1bd-bc88-4890-a644-04a84df5052a · inbound

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks cites this paper.

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:26:59.309811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7ad5939a-73f8-40b2-993c-5fe2b2a0181f · inbound

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots cites this paper.

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T02:09:22.521177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 89595de1-b9ad-4080-a147-1ed5fd276557 · inbound

Investigating The Security of Modern AI and Cloud Infrastructure cites this paper.

Investigating The Security of Modern AI and Cloud Infrastructure Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 137

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:29:42.325046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e938f8b3-7d40-4f1f-9857-d41e30c67f32 · inbound

ToxiREX: A Dataset on Toxic REasoning in ConteXt cites this paper.

ToxiREX: A Dataset on Toxic REasoning in ConteXt Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 223

Resolution: verified exact; arxiv_id, observed 2026-06-29T04:43:07.121701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ccf75546-7565-452c-b4bb-2286973270ba · inbound

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety cites this paper.

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 104

Resolution: unresolved; no resolver link, observed 2026-07-12T14:28:50.627444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 121b3da8-53a6-49bf-a5ae-cf67e5e61b74 · inbound

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions cites this paper.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.097166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dde8f715-429a-4a7b-a486-671e594e1b93 · inbound

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions cites this paper.

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-01T18:55:01.084617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a179e9a-bb3b-445a-b683-f7a1f9e23786 · inbound

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs cites this paper.

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T16:06:05.960205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers