37 citations · 106 across the 13 of their papers we have counts for
3 papers · 1 filter
Understanding and Diagnosing Vulnerability under Adversarial Attacks
Haizhong Zheng, Ziqi Zhang, Honglak Lee +1
Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. Currently, there is no clear insight into how slight perturbations cause such a large difference in c…
Towards Robustness against Unsuspicious Adversarial Examples
Liang Tong, Minzhe Guo, Atul Prakash +1
Despite the remarkable success of deep neural networks, significant concerns have emerged about their robustness to adversarial perturbations to inputs. While most attacks aim to e…
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
Sanjay Kariyappa, Atul Prakash, Moinuddin Qureshi
Model Stealing (MS) attacks allow an adversary with black-box access to a Machine Learning model to replicate its functionality, compromising the confidentiality of the model. Such…