206 citations · 241 across the 8 of their papers we have counts for
8 papers
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
ShengYun Peng, Weilin Xu, Cory Cornelius +6
Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a sui…
RobArch: Designing Robust Architectures against Adversarial Attacks
ShengYun Peng, Weilin Xu, Cory Cornelius +4
Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the a…
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
Xinlei He, Zheng Li, Weilin Xu +2
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to infer whether an input sample w…
Synthetic Dataset Generation for Adversarial Machine Learning Research
Xiruo Liu, Shibani Singh, Cory Cornelius +4
Existing adversarial example research focuses on digitally inserted perturbations on top of existing natural image datasets. This construction of adversarial examples is not realis…
Toward Few-step Adversarial Training from a Frequency Perspective
Hans Shih-Han Wang, Cory Cornelius, Brandon Edwards +1
We investigate adversarial-sample generation methods from a frequency domain perspective and extend standard Projected Gradient Descent (PGD) to the frequency domain.…
Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA
Cory Cornelius, Shang-Tse Chen, Jason Martin +1
In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios. We describe how we use…