Yi-Fan Chen

Transferable Unrestricted Attacks via Holistic Inversion and Implicit Cross-Attention Regularization

Pre-trained vision backbones, which are widely reused in automation and embodied perception systems, may be vulnerable to transfer-based adversarial attacks. A persistent challenge is to achieve strong transferability while preserving high perceptual fidelity of the adversarial examples. This work presents the Holistic...