Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation

ArXi:2504.16474v2 Announce Type: replace-cross The transfer-based black-box adversarial attack setting poses the challenge of crafting an adversarial example (AE) on known surrogate models that remain effective against unseen target models. Due to the practical importance of this task, numerous methods have been proposed to address this challenge. However, most previous methods are heuristically designed and intuitively justified, lacking a theoretical foundation. To bridge this gap, we derive a novel transferability bound that offers provable guarantees for adversarial transferability.