GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to be challenging, and the methods relying on detecting adversarial samples are only valid when the attacker is oblivious to the detection mechanism. In this paper we propose a principled adversarial example detection method that can withstand norm-constrained white-box attacks. Inspired by one-versus-the-rest classification, in a K class classification problem, we train K binary classifiers where the i-th binary classifier is used to distinguish between clean data of class i and adversarially perturbed samples of other classes. At test time, we first use a trained classifier to get the predicted label (say k) of the input, and then use the k-th binary classifier to determine whether the input is a clean sample (of class k) or an adversarially perturbed example (of other classes). We further devise a generative approach to detecting/classifying adversarial examples by interpreting each binary classifier as an unnormalized density model of the class-conditional data. We provide comprehensive evaluation of the above adversarial example detection/classification methods, and demonstrate their competitive performances and compelling properties.
Code (1)
Tasks
ClassificationGeneral ClassificationRobust classificationvalidSimilar Papers 제목 키워드 기반
GAT: Generative Adversarial Training for Adversarial Example Detection and Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to …
General ClassificationRobust classificationvalidGenerating Adversarial Malware Examples for Black-Box Attacks Based on GAN
Machine learning has been used to detect new malware in recent years, while malware authors have strong motivation to attack such algorithms. Malware authors usually have no access to the detailed structures and paramete…
BIG-bench Machine LearningGenerative Adversarial NetworkMalware DetectionSynthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unres…
Objectobject-detectionObject DetectionNovelty Detection via Non-Adversarial Generative Network
One-class novelty detection is the process of determining if a query example differs from the training examples (the target class). Most of previous strategies attempt to learn the real characteristics of target sample b…
DecoderImage ReconstructionNovelty DetectionDisentangling Adversarial Robustness in Directions of the Data Manifold
Using generative models (GAN or VAE) to craft adversarial examples, i.e. generative adversarial examples, has received increasing attention in recent years. Previous studies showed through experiments that the generative…
Adversarial Robustness