Siyue Wang

Latest

• Intrinsic Examples: Robust Fingerprinting of Deep Neural Networks
• AdvMS: A Multi-Source Multi-Cost Defense Against Adversarial Attacks
• Block Switching: A Stochastic Approach for Deep Learning Security
• Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
• Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks