 Evaluating Explanation Methods for Deep Learning in SecurityEuropean Symposium on Security and Privacy (EuroS&P), 2019 |
 Robust Attribution RegularizationNeural Information Processing Systems (NeurIPS), 2019 |
 Functional Transparency for Structured Data: a Game-Theoretic ApproachInternational Conference on Machine Learning (ICML), 2019 |
 Understanding Impacts of High-Order Loss Approximations and Features in
Deep Learning InterpretationInternational Conference on Machine Learning (ICML), 2019 |
 Knockoffs for the mass: new feature importance statistics with false
discovery guaranteesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2018 |
 Adversarial Reprogramming of Neural NetworksInternational Conference on Learning Representations (ICLR), 2018 |
 Pathologies of Neural Models Make Interpretations DifficultConference on Empirical Methods in Natural Language Processing (EMNLP), 2018 |
