From Threat to Trust: Exploiting Attention Mechanisms for Attacks and Defenses in Cooperative Perception

Name: From Threat to Trust: Exploiting Attention Mechanisms for Attacks and Defenses in Cooperative Perception
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Chenyi Wang

34th USENIX Security Symposium (USENIX Security '25) · Day 3 · ML and AI Security 4: Robustness