Feature-aware transferable adversarial attacks against image classification

Shuyan Cheng, Peng Li, Keji Han, He Xu

Abstract: Highlights•An attack framework based on a feature-aware triplet is proposed.•Achieve a better tradeoff between attack capability and transferability.•A weighted average method for constructing a feature library is designed.•Define more expressive sample spaces.•Extended experiments exhibit superior transferability of the proposed FTA.