RVCL: Evaluating the robustness of contrastive learning via verification

Z Wang, W Liu - Journal of Machine Learning Research, 2023 - jmlr.org
Contrastive adversarial training has successfully improved the robustness of contrastive
learning (CL). However, the robustness metric in these methods depends on attack …

[PDF][PDF] A Survey on Image Perturbations for Model Robustness: Attacks and Defenses

PF Zhang, Z Huang - researchgate.net
The widespread adoption of deep neural networks (DNNs) has raised significant concerns
about their robustness, particularly in real-world environments characterized by inherent …