Paper Info
Title
Reinforced Adversarial Attacks on Deep Neural Networks Using ADMM.
Abstract
As deep learning penetrates into wide application domains, it is essential to evaluate the robustness of deep neural networks (DNNs) under adversarial attacks, especially for some security-critical applications. To better understand the security properties of DNNs, we propose a general framework for constructing adversarial examples, based on ADMM (Alternating Direction Method of Multipliers). This general framework can be adapted to implement L2 and L0 attacks with minor changes. Our ADMM attacks require less distortion for incorrect classification compared with C&W attacks. Our ADMM attack is also able to break defenses such as defensive distillation and adversarial training, and provide strong attack transferability.
Year
DOI
Venue
2018
10.1109/GlobalSIP.2018.8646651
IEEE Global Conference on Signal and Information Processing
Keywords
Field
DocType
Deep Neural Networks,Adversarial Attacks,ADMM (Alternating Direction Method of Multipliers)
Computer science,Robustness (computer science),Security properties,Artificial intelligence,Deep learning,Distortion,Transferability,Deep neural networks,Adversarial system
Conference
ISSN
Citations 
PageRank 
2376-4066
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Pu Zhao13211.73
KaiDi Xu2388.42
Tianyun Zhang3316.42
Makan Fardad454741.98
Yanzhi Wang51082136.11
Xue Lin68614.97