PrototypeCommon
reds-lab/Narcissus
The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.
- Owner
- reds-lab (organization)
- Stars
- Stars: 126
- Forks
- Forks: 15
- Language
- Python
- License
- MIT
- Created
- 2022
- Topics
- deep-adversarial-attacksadversarial-machine-learningai-securitybackdoor-attackspoisoning-attacks
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- yuzushi-dev/hermes-seoStars: 126PythonPrototype
- markklab1903d9/CS2-FPS-Optimizer-Performance-Boost-Lag-Fix-Tool-2026Stars: 126PythonPrototype
- o-Sakurajimamai-o/cet-practiceStars: 126PythonPrototype
- agiliq/DinetteStars: 126PythonPrototype
- miracle2k/android2poStars: 126PythonPrototype
- deldotdr/txRedisStars: 126PythonPrototype