224 citations · 3.2k across the 170 of their papers we have counts for
24 papers · 1 filter
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…
The Search for Sparse, Robust Neural Networks
Justin Cosentino, Federico Zaiter, Dan Pei +1
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters…
Triple Generative Adversarial Networks
Chongxuan Li, Kun Xu, Jiashuo Liu +2
We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax gam…
Design and Interpretation of Universal Adversarial Patches in Face Detection
Xiao Yang, Fangyun Wei, Hongyang Zhang +1
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous wor…
Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure
Zhijie Deng, Yucen Luo, Jun Zhu +1
Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayes…
Generative Well-intentioned Networks
Justin Cosentino, Jun Zhu
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative networ…