3 papers
cs.CV2026
A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Models
Wutao Chen, Huaqin Zou, Chen Wan +1
Vision-language pre-training (VLP) models are vulnerable to adversarial examples, particularly in black-box scenarios. Existing multimodal attacks often suffer from limited perturb…
cs.CV2025
Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation
Zihong Guo, Chen Wan, Yayin Zheng +2
The transferability of adversarial examples poses a significant security challenge for deep neural networks, which can be attacked without knowing anything about them. In this pape…
cs.CV2025
Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion
Yayin Zheng, Chen Wan, Zihong Guo +2
Adversarial attacks have become a significant challenge in the security of machine learning models, particularly in the context of black-box defense strategies. Existing methods fo…