BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target

Name: BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target
Duration: 15 min
Description: Talk from IEEE Symposium on Security and Privacy 2025.

Guangyu Shen, Siyuan Cheng, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Hanxi Guo

IEEE Symposium on Security and Privacy 2025 · Day 2 · ML Attacks