9 citations · 17 across the 2 of their papers we have counts for
2 papers
cs.CV2022★ 8 cited
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
Yiqi Zhong, Xianming Liu, Deming Zhai +2
Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to…
cs.LG2022★ 9 cited
Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
Yiqi Zhong, Lei Wu, Xianming Liu +1
Robustness of deep neural networks (DNNs) to malicious perturbations is a hot topic in trustworthy AI. Existing techniques obtain robust models given fixed datasets, either by modi…