poisoning-attacks topic
mlsec
PhD/MSc course on Machine Learning Security (Univ. Cagliari)
AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
secml
A Python library for Secure and Explainable Machine Learning
flPapers
Paper collection of federated learning. Conferences and Journals Collection for Federated Learning from 2019 to 2021, Accepted Papers, Hot topics and good research groups. Paper summary
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...
rethinking-backdoor-attacks
awesome-recsys-poisoning
A Survey of Poisoning Attacks and Defenses in Recommender Systems