NDSS 2018 - Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Session 3A: Deep Learning and Adversarial ML - 04 Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
SUMMARY
Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by adversarial examples that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, feature squeezing, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model’s prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.
SLIDES
http://wp.internetsociety.org/ndss/wp...
PAPER
https://www.ndss-symposium.org/wp-con...
AUTHORS
Weilin Xu (University of Virginia)
David Evans (University of Virginia)
Yanjun Qi (University of Virginia)
Network and Distributed System Security (NDSS) Symposium 2018, 18-21 February 2018, Catamaran Resort Hotel & Spa in San Diego, California.
https://www.ndss-symposium.org/ndss20...
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.
https://www.ndss-symposium.org/
#NDSS #NDSS18 #NDSS2018 #InternetSecurity