FlipAttack: Jailbreak LLMs via Flipping

Yue Liu, Xiao-Xin He, Miao Xiong, Jinlan Fu, Shumin Deng +3 more
2/14/2026

No official code found. Best implementation: yueliu1999/FlipAttack (182 stars, last commit 2025-05-02).

Semantic Scholar

Code Implementations(1)

yueliu1999/FlipAttackCommunity67%

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

18215PythonOct 2, 20241 years ago
aijailbreakllmllmssafety+1 more

Similar Papers

BiMatting: Efficient Video Matting via Binarization

100% match1 repo382026

Visual Instruction Inversion: Image Editing via Image Prompting

99% match2026

COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation

99% match1 repo242026

GiLOT: Interpreting Generative Language Models via Optimal Transport

99% match2026

Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO

99% match1 repo82026

ContraDiff: Planning Towards High Return States via Contrastive Learning

99% match2026

Cite this paper

@article{liu2026flipattack,
  title  = {FlipAttack: Jailbreak LLMs via Flipping},
  author = {Yue Liu and Xiao-Xin He and Miao Xiong and Jinlan Fu and Shumin Deng and Yingwei Ma and Jiaheng Zhang and Bryan Hooi},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:3d473f1da34cb513af2f9e51f103b7b8db59a2ea},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3d473f1da34cb513af2f9e51f103b7b8db59a2ea.svg)](https://codeofpaper.com/paper/3d473f1da34cb513af2f9e51f103b7b8db59a2ea)

Discussion