11 citations · 22 across the 5 of their papers we have counts for
5 papers · 1 filter
Solving Trojan Detection Competitions with Linear Weight Classification
Todd Huster, Peter Lin, Razvan Stefanescu +2
Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access t…
TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation
Todd Huster, Emmanuel Ekwedike
Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection…
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
Todd Huster, Jeremy E. J. Cohen, Zinan Lin +5
Generative adversarial networks (GANs) are often billed as "universal distribution learners", but precisely what distributions they can represent and learn is still an open questio…
Universal Lipschitz Approximation in Bounded Depth Neural Networks
Jeremy E. J. Cohen, Todd Huster, Ra Cohen
Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learnin…
Limitations of the Lipschitz constant as a defense against adversarial examples
Todd Huster, Cho-Yu Jason Chiang, Ritu Chadha
Several recent papers have discussed utilizing Lipschitz constants to limit the susceptibility of neural networks to adversarial examples. We analyze recently proposed methods for…