396 citations · 1.6k across the 95 of their papers we have counts for
Showing 2023 · cs.CVShow all
3 papers · 2 filters
cs.CV2023
Reducing Adversarial Training Cost with Gradient Approximation
Huihui Gong
Deep learning models have achieved state-of-the-art performances in various domains, while they are vulnerable to the inputs with well-crafted but small perturbations, which are na…
cs.CV2023★ 1 cited
Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks
Huihui Gong, Minjing Dong, Siqi Ma +3
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single ty…
cs.CV2023★ 1 cited
Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
Huihui Gong, Minjing Dong, Siqi Ma +3
Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking…