Secure Transfer Learning: Training Clean Model Against Backdoor in Pre-Trained Encoder and Downstream Dataset

Name: Secure Transfer Learning: Training Clean Model Against Backdoor in Pre-Trained Encoder and Downstream Dataset
Duration: 15 min
Description: Talk from IEEE Symposium on Security and Privacy 2025.

Yechao Zhang, Yuxuan Zhou, Tianyu Li, Minghui Li, Shengshan Hu, Wei Luo

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