yueliu1999 / FlipAttack
[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".
Why this job: says: jailbreak; topics: security, jailbreak
What it does
Figure 1. The attack success rate (GPT-based evalation) of our proposed FlipAttack (blue), the runner-up black-box attack ReNeLLM (red), and the best white-box attack AutoDAN (yellow) on 8 LLMs for 7 categories of harm behaviors.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 182
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| AISecurityLab / hackagent | 535 | 7 days ago | Apache-2.0 | Mac, Windows, Linux |
| Sekolah76 / syadagentic | 103 | 2 months ago | MIT | No downloads |
| SantanderAI / autoguardrails | 129 | 3 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- ai
- jailbreak
- llm
- llms
- safety
- security
Project record
- JobAI security
- StatusListed
- Commits40
- Forks15
- Watching4
- Stars in 28 days+1
- CreatedOct 2, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026