most citedTowards Interpretable Deep Neural Networks by Leveraging Adversarial Examples

88 citations · 171 across the 6 of their papers we have counts for

collaborators

6 papers

cs.HC20203 cited

Analyzing the Noise Robustness of Deep Neural Networks

Kelei Cao, Mengchen Liu, Hang Su +3

Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predicti…

cs.CV201921 cited

Benchmarking Adversarial Robustness

Yinpeng Dong, Qi-An Fu, Xiao Yang +4

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts h…

cs.LG20191 cited

Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork

Yulong Wang, Xiaolin Hu, Hang Su

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwo…

cs.CV201915 cited

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

Yinpeng Dong, Hang Su, Baoyuan Wu +4

Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to ad…

cs.CV201943 cited

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Yinpeng Dong, Tianyu Pang, Hang Su +1

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is…

cs.LG201988 cited

Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples

Yinpeng Dong, Fan Bao, Hang Su +1

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it…