LLM Jailbreak Attacks

LLM: Large Language Model

Overview

LLM jailbreak research examines how prompts and interactions can circumvent safety alignment, and how to make models resist those attempts. Attacks range from roleplay, obfuscation, and multi-turn persuasion to automated prompt optimization, internal activation steering, and attacks on audio, code, and tool-using agents. Defenses include input filters, intent detectors, safety fine-tuning, representation-level interventions, and safeguards that track risk across a conversation; evaluations increasingly test diverse languages, adaptive attacks, and harmful actions that actually execute. A central challenge is improving robustness without rejecting benign requests, while inconsistent judges, budgets, and test settings make reported attack success difficult to compare.

Latest papers

CardsList

217 papers13 papers in the last four weeks, down 43% on the four weeks before. 0.1% of all new papers.

  1. BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

    Jun 3, 2025Kalyan Nakka, Nitesh SaxenaJailbreak AttacksLLM Jailbreak Attacks

  2. Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models

    May 12, 2025Haoran Gu, Handing Wang, Yi Mei +2LLM Safety AlignmentLLM Safety

  3. Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

    Mar 8, 2025Thomas Winninger, Boussad Addad, Katarzyna KapustaAdversarial Prompt GenerationAdversarial Attacks on LLMs

  4. GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods

    Feb 24, 2025Ruixuan Huang, Xunguang Wang, Zongjie Li +2Language Model Safety EvaluationLLM Jailbreak Attacks

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

    Dec 10, 2024Xiaoqun Liu, Weiming Qi, Qiben YanAdversarial Robustness of Language ModelsLLM Jailbreak Attacks

  6. Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge

    Apr 8, 2024Weikai Lu, Ziqian Zeng, Jianwei Wang +5LLM Safety AlignmentLLM Jailbreak Attacks