Random Directional Attack for Fooling Deep Neural Networks

Abstract

Deep neural networks (DNNs) have been widely used in many fields such as images processing, speech recognition; however, they are vulnerable to adversarial examples, and this is a security issue worthy of attention. Because the training process of DNNs converge the loss by updating the weights along the gradient descent direction, many gradient-based methods attempt to destroy the DNN model by adding perturbations in the gradient direction. Unfortunately, as the model is nonlinear in most cases, the addition of perturbations in the gradient direction does not necessarily increase loss. Thus, we propose a random directed attack (RDA) for generating adversarial examples in this paper. Rather than limiting the gradient direction to generate an attack, RDA searches the attack direction based on hill climbing and uses multiple strategies to avoid local optima that cause attack failure. Compared with state-of-the-art gradient-based methods, the attack performance of RDA is very competitive. Moreover, RDA can attack without any internal knowledge of the model, and its performance under black-box attack is similar to that of the white-box attack in most cases, which is difficult to achieve using existing gradient-based attack methods.

arXiv comment13pages

References in corpus (17)

• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Synthesizing Robust Adversarial Examples
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Adversarially Robust Generalization Requires More Data
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Adversarial Examples Are Not Bugs, They Are Features
• Detecting Adversarial Samples from Artifacts
• On the (Statistical) Detection of Adversarial Examples
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Did you hear that? Adversarial Examples Against Automatic Speech Recognition
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
• Adversarial examples from computational constraints
• HotFlip: White-Box Adversarial Examples for Text Classification
• Divide, Denoise, and Defend against Adversarial Attacks
• Intriguing Properties of Adversarial Examples
• Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples