
PeerAiD proposes a novel approach to adversarial distillation by training a peer network specialized in defending the student network, resulting in significantly higher robustness. The method improves both the robust accuracy and natural accuracy of the student network compared to various baselines.


coremsg

peeraid-enhancing-adversarial-distillation-with-specialized-peer-tutoring


PeerAiD: Enhancing Adversarial Distillation with Specialized Peer Tutoring


title_rewrite


PeerAiD proposes a novel method in adversarial distillation, training a peer network to defend against student-generated adversarial examples, achieving higher robustness and natural accuracy.


peeraid-improving-adversarial-distillation-from-a-specialized-peer-tutor-in-neural-networks


PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor in Neural Networks



PeerAiD improves adversarial robustness by training a specialized peer network to defend against student-generated adversarial examples.


peeraid-improving-adversarial-distillation-with-specialized-peer-tutoring


PeerAiD: Improving Adversarial Distillation with Specialized Peer Tutoring
