Lei Lu

Ada-MGNS: Enhancing Black-Box Transfer Attacks on Vision Transformers via Adaptive Momentum and Deep Attention Guidance

Transfer-based black-box attacks are an important tool for evaluating deployed vision models, yet adversarial examples generated from Vision Transformer (ViT) surrogates often exhibit limited cross-architecture transferability. Existing momentum-based attacks are effective for convolutional neural network (CNN) surroga...