Teach Me to Trick: Exploring Adversarial Transferability via Knowledge Distillation

Abstract

We investigate whether knowledge distillation (KD) from multiple heterogeneous teacher models can enhance the generation of transferable adversarial examples. A lightweight student model is trained using two KD strategies: curriculum-based switching and joint optimization, with ResNet50 and DenseNet-161 as teachers. The trained student is then used to generate adversarial examples using FG, FGS, and PGD attacks, which are evaluated against a black-box target model (GoogLeNet). Our results show that student models distilled from multiple teachers achieve attack success rates comparable to ensemble-based baselines, while reducing adversarial example generation time by up to a factor of six. An ablation study further reveals that lower temperature settings and the inclusion of hard-label supervision significantly enhance transferability. These findings suggest that KD can serve not only as a model compression technique but also as a powerful tool for improving the efficiency and effectiveness of black-box adversarial attacks.