129 citations · 459 across the 10 of their papers we have counts for
3 papers · 1 filter
ML-LOO: Detecting Adversarial Examples with Feature Attribution
Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh +2
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation…
HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
Jianbo Chen, Michael I. Jordan, Martin J. Wainwright
The goal of a decision-based adversarial attack on a trained model is to generate adversarial examples based solely on observing output labels returned by the targeted model. We de…
LS-Tree: Model Interpretation When the Data Are Linguistic
Jianbo Chen, Michael I. Jordan
We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importa…