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.

Date Created 2022-04-08 (2 years ago)

Commits 59 (last one about a year ago)

Stargazers 100 (0 this week)

Watchers 2 (0 this week)

Forks 11

License mit

Ranking

RepositoryStats indexes 564,918 repositories, of these reds-lab/Narcissus is ranked #283,423 (50th percentile) for total stargazers, and #467,289 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #51,923/111,200.

Other Information

reds-lab/Narcissus has Github issues enabled, there are 6 open issues and 4 closed issues.

Homepage URL: https://arxiv.org/pdf/2204.05255.pdf

All Topics

deep- ai-security backdoor-attacks poisoning-attacks adversarial-attacks adversarial-machine-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

59 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-08-27 @ 12:06am, id: 479534670 / R_kgDOHJUeTg