1.9k citations · 2k across the 8 of their papers we have counts for
4 papers · 1 filter
Security Risks in Deep Learning Implementations
Qixue Xiao, Kang Li, Deyue Zhang +1
Advance in deep learning algorithms overshadows their security risk in software implementations. This paper discloses a set of vulnerabilities in popular deep learning frameworks i…
Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
Weilin Xu, David Evans, Yanjun Qi
Feature squeezing is a recently-introduced framework for mitigating and detecting adversarial examples. In previous work, we showed that it is effective against several earlier met…
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Weilin Xu, David Evans, Yanjun Qi
Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purpo…
DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
Ji Gao, Beilun Wang, Zeming Lin +2
Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attack…