On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces

2018/09/24 by Chia-Yi Hsu, Pei-Hsuan Lu, Hsu, Chia-Yi +5
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1809.08986

openalex publication_date 2018/09/24 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

Recent studies have found that deep learning systems are vulnerable to adversarial examples; e.g., visually unrecognizable adversarial images can easily be crafted to result in misclassification. The robustness of neural networks has been studied extensively in the context of adversary detection, which compares a metric that exhibits strong discriminate power between natural and adversarial examples. In this paper, we propose to characterize the adversarial subspaces through the lens of mutual information (MI) approximated by conditional generation methods. We use MI as an information-theoretic metric to strengthen existing defenses and improve the performance of adversary detection. Experimental results on MagNet defense demonstrate that our proposed MI detector can strengthen its robustness against powerful adversarial attacks.

Citations

• Towards Deep Learning Models Resistant to Adversarial Attacks
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples
• On the Limitation of MagNet Defense against L₁-based Adversarial Examples
• MagNet: a Two-Pronged Defense against Adversarial Examples
• Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models

Related

• Improving Adversarial Robustness via Mutual Information Estimation
• Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense
• MagNet: a Two-Pronged Defense against Adversarial Examples
• Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information
• Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning