Tian Su

AUTE: Peer-Alignment and Self-Unlearning Boost Adversarial Robustness for Training Ensemble Models

Adversarial attacks poses a significant threat to the security of AI-based systems. To counteract these attacks, adversarial training (AT) and ensemble learning (EL) have emerged as widely adopted methods for enhancing model robustness. However, a counter-intuitive phenomenon arises where the simple…