EVA: Editing for Versatile Alignment against Jailbreaks

Abstract

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent defenses typically rely on safety fine-tuning or external filters to reduce the model's likelihood of producing harmful content. While effective to some extent, these methods often incur significant computational overheads and suffer from the safety utility t

Categories

Framework mappings

Suggested from the entry's categories.

@misc{wang2026eva,
  title = {{EVA: Editing for Versatile Alignment against Jailbreaks}},
  author = {Yi Wang and Hongye Qiu and Yue Xu and Sibei Yang and Zhan Qin and Minlie Huang and Wenjie Wang},
  year = {2026},
  month = may,
  eprint = {2605.14750},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.14750}
}