BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
Security researchers examine technical aspects of BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
IEEE Symposium on Security and Privacy·14 min
Explanation-Aware Backdoors
Industry experts analyze emerging threats surrounding Disguising Attacks with Explanation-Aware Backdoors.
disguisingattackexplanation-aware+1
IEEE Symposium on Security and Privacy·25 min
Security researchers examine technical aspects of Eliminating Input-Based Attacks by Deriving Encoders and Decoders from CFGs.
eliminatinginput-basedattack+3
IEEE Symposium on Security and Privacy·13 min
Analysts investigate attack surfaces and defenses concerning 185 BadVFL backdoor attacks in vertical federated learning Mohammad Naseri.
backdoorbadvflattack+3