Toward Defending Adversarial Patch Attacks With Mask-Reconstruction-Assisted Adversarial Training
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2025.3629619
Abstract: Adversarial patch attacks pose a significant threat to deep learning models in real-world applications, such as autonomous driving, due to their physical feasibility and ease of deployment. Although several defenses exist, they often have limitations,… read more here.
Keywords: patch; adversarial training; mask reconstruction; patch attacks ... See more keywords