mlsanityData to 7 Oct 2026

FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)

arXiv 2408.16163 ↗First posted 28 Aug 2024cs.CL cs.AIcited by 6

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

This paper introduces FRACTURED-SORRY-Bench, a framework for evaluating the safety of Large Language Models (LLMs) against multi-turn conversational attacks. Building upon the SORRY-Bench dataset, we propose a simple yet effective method for generating adversarial prompts by breaking down harmful queries into seemingly innocuous sub-questions. Our approach achieves a maximum increase of +46.22% in Attack Success Rates (ASRs) across GPT-4, GPT-4o, GPT-4o-mini, and GPT-3.5-Turbo models compared to baseline methods. We demonstrate that this technique poses a challenge to current LLM safety measures and highlights the need for more robust defenses against subtle, multi-turn attacks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 14 of its 20 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

14 of 20 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  2. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  4. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  3. 2022Red Teaming Language Models with Language Modelscited by 983
  4. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 224
  5. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
  6. 2023Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMscited by 176
  7. 2024ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teamingcited by 96
  8. 2023SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Modelscited by 72
  9. 2024Risks of AI Scientists: Prioritizing Safeguarding Over Autonomycited by 49
  10. 2023Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitizationcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2026Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithmscited by 3
  3. 2024Knowledge Graph Guided Evaluation of Abstention Techniquescited by 2
  4. 2026NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agentscited by 1
  5. 2026Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systemscited by 1
  6. 2026Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversationscited by 0