当前位置：首页
> read paper
论文解读《Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks》
发表时间：2019 期刊会议：IEEE Symposium on Security and Privacy (S&P) 论文单位：UC Santa Barbara 论文作者：Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal...
论文泛读《T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification》
发表时间：2021 期刊会议：30th USENIX Security Symposium 论文单位：Virginia Tech 论文作者：Ahmadreza Azizi，Ibrahim Asadullah Tahmid，Asim Waheed，Neal Mangaokar，Jiameng Pu，M...
