摘要: > "Gu, Tianyu, et al. "Badnets: Evaluating backdooring attacks on deep neural networks." IEEE Access 7 (2019): 47230-47244." 本文提出了外包机器学习时选择值得信赖的提供商的重要 阅读全文
posted @ 2023-06-27 21:11 方班隐私保护小组 阅读(89) 评论(0) 推荐(0) 编辑
摘要: > "Liu, Kang, Brendan Dolan-Gavitt, and Siddharth Garg. "Fine-pruning: Defending against backdooring attacks on deep neural networks." Research in Att 阅读全文
posted @ 2023-06-27 20:48 方班隐私保护小组 阅读(70) 评论(0) 推荐(0) 编辑
摘要: > "Wang, Haotao, et al. "Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork." Advances in Neural Informa 阅读全文
posted @ 2023-06-27 17:47 方班隐私保护小组 阅读(44) 评论(0) 推荐(0) 编辑
摘要: > "Wu, Dongxian, and Yisen Wang. "Adversarial neuron pruning purifies backdoored deep models." Advances in Neural Information Processing Systems 34 (2 阅读全文
posted @ 2023-06-27 16:24 方班隐私保护小组 阅读(93) 评论(0) 推荐(0) 编辑