Defending Adversarial Examples via DNN Bottleneck Reinforcement
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks. Typical DNN classifiers encode the input image into a compressed latent representation more suitable for inference. This information bottleneck makes a trade-off between the image-specific structure and class-specific information in an image. By reinforcing the former while maintaining the latter, any redundant information, be it adversarial or not, should be removed from the latent representation. Hence, this paper proposes to jointly train an auto-encoder (AE) sharing the same encoding weights with the visual classifier. In order to reinforce the information bottleneck, we introduce the multi-scale low-pass objective and multi-scale high-frequency communication for better frequency steering in the network. Unlike existing approaches, our scheme is the first reforming defense per se which keeps the classifier structure untouched without appending any pre-processing head and is trained with clean images only. Extensive experiments on MNIST, CIFAR-10 and ImageNet demonstrate the strong defense of our method against various adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle
Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the final robustness of models during AT, th…
Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been propo…
Adversarial AttackDefending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference at…
BIG-bench Machine LearningInference AttackMagNet: a Two-Pronged Defense against Adversarial Examples
Deep learning has shown promising results on hard perceptual problems in recent years. However, deep learning systems are found to be vulnerable to small adversarial perturbations that are nearly imperceptible to human. …
Deep LearningVocal Bursts Valence PredictionAn Adversarial Attack Defending System for Securing In-Vehicle Networks
In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication protocol, such as Controller Area Network (C…
Adversarial Attack