Adversarial Machine Learning

Reducing classifier overconfidence against adversaries through graph algorithms

Adversarial Machine Learning: A New Threat Paradigm for Next-generation Wireless Communications

Runtime Monitoring of Deep Neural Networks Using Top-Down Context Models Inspired by Predictive Processing and Dual Process Theory

Trinity: Trust, Resilience and Interpretability of Machine Learning Models

Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification

Adversarial Distillation of Bayesian Neural Networks

Attribution-driven causal analysis for detection of adversarial examples

Attribution-based confidence metric for deep neural networks

Detecting adversarial examples using data manifolds