Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks
No ratings
Presented at USENIX Security 2022 by
In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing defenses, by tracing back a successful attack to its root cause, and offering a path forward for mitigation to prevent similar attacks in the future.