Video Motion Blur Attack via Grad-Weighted and Discrete-Fusion Based Perturbation Generation
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2025.3535307
Abstract: Recent research has shown that deep learning networks are vulnerable to adversarial samples. Although there has been great progress in the study of adversarial attacks on images, there is relatively little research on adversarial attacks… read more here.
Keywords: motion; fusion; blur attack; motion blur ... See more keywords