293 citations · 348 across the 3 of their papers we have counts for
3 papers
cs.LG2021★ 35 cited
Anti-Backdoor Learning: Training Clean Models on Poisoned Data
Yige Li, Xixiang Lyu, Nodens Koren +3
Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing ba…
cs.LG2020★ 20 cited
SoK: Certified Robustness for Deep Neural Networks
Linyi Li, Tao Xie, Bo Li
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adve…
cs.CR2018★ 293 cited
Adversarial Attack and Defense on Graph Data: A Survey
Lichao Sun, Yingtong Dou, Carl Yang +5
Deep neural networks (DNNs) have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However,…