Search Results for author: Pei-Hsuan Lu

Found 3 papers, 2 papers with code

On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces

no code implementations24 Sep 2018 Chia-Yi Hsu, Pei-Hsuan Lu, Pin-Yu Chen, Chia-Mu Yu

Recent studies have found that deep learning systems are vulnerable to adversarial examples; e. g., visually unrecognizable adversarial images can easily be crafted to result in misclassification.

On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples

1 code implementation14 Apr 2018 Pei-Hsuan Lu, Pin-Yu Chen, Kang-Cheng Chen, Chia-Mu Yu

In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and security.

On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples

1 code implementation26 Mar 2018 Pei-Hsuan Lu, Pin-Yu Chen, Chia-Mu Yu

Understanding and characterizing the subspaces of adversarial examples aid in studying the robustness of deep neural networks (DNNs) to adversarial perturbations.

Cannot find the paper you are looking for? You can Submit a new open access paper.