On the Adversarial Transferability of Generalized "Skip Connections"

ArXi:2410.08950v2 Announce Type: replace-cross Skip connection is an essential ingredient for modern deep models to be deeper and powerful. Despite their huge success in normal scenarios (state-of-the-art classification performance on natural examples), we investigate and identify an interesting property of skip connections under adversarial scenarios, namely, the use of skip connections allows easier generation of highly transferable adversarial examples.