Overview

Jailbreak defense studies attacks that disguise, encode, or gradually reveal harmful intent, and how to protect language and multimodal models without blocking legitimate requests. Common approaches include guard classifiers and input rewriting, safety fine-tuning or unlearning, and inference-time methods such as refusal steering, hidden-state monitoring, and selective regeneration. Recent work increasingly tracks intent across conversation turns and addresses multilingual, image, and audio inputs, using benchmarks such as HarmBench, JailbreakBench, and XSTest. No single defense works across all attacks: the central challenge is balancing robustness against adaptive and shifted attacks with false refusals, capability loss, latency, and reliable evaluation on realistic benign inputs.

Latest papers

CardsList

65 papers5 papers in the last four weeks, down 17% on the four weeks before. 0.0% of all new papers.

  1. Sparse Autoencoders are Capable LLM Jailbreak Mitigators

    Feb 12, 2026Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3Sparse AutoencodersLLM Jailbreak Attacks

  2. Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

    Oct 15, 2025Jonghyun Park, Minhyuk Seo, Chaewon Yeo +1Multimodal RobustnessLLM Safety Alignment

  3. 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

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

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