Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature

• Main Authors: Weng, Juanjuan, Luo, Zhiming, Lin, Dazhen, Li, Shaozi, Zhong, Zhun
• Format: Journal Article
• Language: English
• Published: 02.05.2023
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Cryptography and Security

Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models. To improve the transferability of adversarial samples, several feature-based adversarial attack methods hav...