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

arXiv: https://arxiv.org/abs/2408.16163 · HTML: https://mlsanity.com/paper/2408.16163/

## Key facts

- Cited by 6 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming](https://mlsanity.com/paper/2404.08676/) (2024)
- [SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models](https://mlsanity.com/paper/2311.08370/) (2023)
- [Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy](https://mlsanity.com/paper/2402.04247/) (2024)
- [Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization](https://mlsanity.com/paper/2305.15008/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms](https://mlsanity.com/paper/2604.21131/) (2026)
- [Knowledge Graph Guided Evaluation of Abstention Techniques](https://mlsanity.com/paper/2412.07430/) (2024)
- [NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents](https://mlsanity.com/paper/2601.14660/) (2026)
- [Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems](https://mlsanity.com/paper/2605.27766/) (2026)
- [Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations](https://mlsanity.com/paper/2606.21082/) (2026)

## 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.