4 citations · 5 across the 4 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo +2
Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains s…
cs.CR2022★ 4 cited
Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo +2
Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper us…