Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning | Paper Citation Record

Observation 51987e9b-db86-4e42-85d4-7ed965eb8c5d · outbound

This paper cites Llama 3 model card.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Llama 3 model card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.697345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e399931-dc77-41bf-a8d0-8557088251a1 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.701802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3af79303-da0c-41c9-affa-cbf70b6b7e2c · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.705776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094b98a7-515f-4d18-b11a-c305be6ca13e · outbound

This paper cites Many-shot jailbreaking.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Many-shot jailbreaking

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.573329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6bb033e1-ce8e-48c9-a83d-809d6234bd9a · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.714194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b95c695c-de00-4f27-8d69-e1594b0a73d9 · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.719204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb0f603f-c2e7-4512-bf45-3b8ccb3bf130 · outbound

This paper cites Language models are few-shot learners.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Language models are few-shot learners

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.724012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62be13bd-c7b2-43f6-9867-100bd8c422fa · outbound

This paper cites Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.727788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfa3eb9-4a42-48a3-abe4-935f61abb4e2 · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.733088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6413099-72d0-4e21-b4d8-71bf0ae35d1e · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.737657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2138c5fa-c552-429f-a962-5fed6f1913ae · outbound

This paper cites Combating misinformation in the age of llms: Opportunities and challenges.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Combating misinformation in the age of llms: Opportunities and challenges

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.742128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d825ee4-f14e-40cc-a7dd-8430b73b6ff0 · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.746178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a5e26a7-1a84-457a-9088-1aecc83d8781 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Multilingual Jailbreak Challenges in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.750811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a878be1-1938-426c-8f49-4cc7ed5d7ebb · outbound

This paper cites Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.755719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc414b65-0879-4503-8536-00c59249ef86 · outbound

This paper cites The Llama 3 Herd of Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.760004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2925ad-506c-4846-a1f8-ed75d3afb945 · outbound

This paper cites Red- teaming for generative ai: Silver bullet or security theater? In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, volume 7, pages 421–437, 2024.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Red- teaming for generative ai: Silver bullet or security theater? In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, volume 7, pages 421–437, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.543563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 86a9f30c-9aee-4579-b0b6-5d765cd04cf8 · outbound

This paper cites Badllama: cheaply removing safety fine-tuning from llama 2-chat 13b, 2024.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Badllama: cheaply removing safety fine-tuning from llama 2-chat 13b, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.531168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4aebbcbf-ea7f-4815-80f5-81b755a6aee6 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.770507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a230f98-a27f-41a7-9c84-bd66a97c4009 · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.774210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641c1b60-bddc-48c9-aeeb-6d8c3eeda8db · outbound

This paper cites Perplexity—a measure of the difficulty of speech recognition tasks.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Perplexity—a measure of the difficulty of speech recognition tasks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.517940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b52040c0-11c3-4c80-9989-2315068e87fa · outbound

This paper cites Mistral 7B.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Mistral 7B

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.781447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1af48f6-8b91-426a-b038-02fffdf6b462 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.785478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5580c03-ad9d-4d82-a648-b82d36d9a824 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.788923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d31ed7c8-b58b-43ea-af7d-f97174656187 · outbound

This paper cites Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.792439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e59b2646-f26c-4178-a01d-b79d06bbc569 · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.796233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774b9cd4-2bb3-44be-9d77-7e489c0def0f · outbound

This paper cites RAIN: Your Language Models Can Align Themselves without Finetuning.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning RAIN: Your Language Models Can Align Themselves without Finetuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.799789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3a996f-7d66-422b-affe-4e8ac9491e96 · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.803418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6e3624-1cf6-460d-a82e-630435d229c8 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.807650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f52b7b31-46da-41ec-815f-3d1ac87b91e2 · outbound

This paper cites Training language models to follow instructions with human feedback.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Training language models to follow instructions with human feedback

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.811437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d98946-ae4a-4eb0-acfd-02da1a80b42a · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.814907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4c7205-f1b4-4f54-b765-64f8e0121f7e · outbound

This paper cites Universal Jailbreak Backdoors from Poisoned Human Feedback.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.818464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8d9d38-736e-4310-821b-d742885177bc · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.822255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4146389d-132b-4bd6-8081-1fe955e307fc · outbound

This paper cites CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.825816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44356f20-045e-4da2-9e84-8b14a768a0dc · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.829433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33988b2a-c35b-48c8-b3ec-b58bdf2dea45 · outbound

This paper cites do anything now.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning do anything now

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.833240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c72ef52-306c-49f2-815e-41f77be8cc23 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Qwen2.5: A party of foundation models, September 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.837049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff03216b-92ee-4574-83e4-69f22ea01aba · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.840899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeec823e-f6ed-45c5-9d6c-b5e2ec9ce37e · outbound

This paper cites OpenChat: Advancing Open-source Language Models with Mixed-Quality Data.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.844524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a8eaf54-aad6-4d17-9a68-39953e2e431d · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.848329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524a50a4-a35c-481a-ac54-2ececa3686b3 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.852850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 1738ef74-4719-47c3-8ad8-c8494ed086b2 · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminder.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Defending chatgpt against jailbreak attack via self-reminder

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.477073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 493da253-3d00-4cab-9e27-74a02732220c · outbound

This paper cites Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.863562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4383d3df-5b9c-40cb-9135-33ab224320d0 · outbound

This paper cites Qwen2 Technical Report.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Qwen2 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.867549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f49797-2e6a-4e80-ad93-790aa4ed03df · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.870948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99b54b90-02ac-41d0-919d-823d6d7cfc14 · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.874542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e088c2cf-5dc4-4985-8771-c216233db363 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.877810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 095ec9a2-ea40-4352-a2c7-27ea35e465f3 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.881332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2ff848-1cfe-45d1-91dd-fbcea379715e · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.885191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f0c01b-75ba-442b-891f-23955059e5e6 · outbound

This paper cites Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.889218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2424d0e2-b828-4159-bed6-f8e2cce7f211 · outbound

This paper cites Diversity Helps Jailbreak Large Language Models.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Diversity Helps Jailbreak Large Language Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-10T20:35:52.997180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1f9f5f83-9ceb-4d85-b6b7-63b0cdaa32b1 · outbound

This paper cites Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.898323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed8e2339-b36c-4fba-a62a-9510ab9119d9 · outbound

This paper cites Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.902122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9476d38-a2a4-4bdb-b25d-3c64abba7121 · outbound

This paper cites Starling-7b: Improving llm helpfulness & harmlessness with rlaif, November 2023.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Starling-7b: Improving llm helpfulness & harmlessness with rlaif, November 2023

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.455117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dea701a4-d2cc-4c57-96ba-73755f0076f1 · outbound

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

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.910697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c3d999-626e-41cc-8893-c678846a02e7 · outbound

This paper cites As shown in Table 10, our method can still achieve remarkable performance on HarmBench [28].

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning As shown in Table 10, our method can still achieve remarkable performance on HarmBench [28]

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:35:53.439187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers