CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator
This addresses the practical deployment challenges of adversarial attacks for security researchers, though it is incremental as it builds on prior generative model-based attacks.
The paper tackles the problem of adversarial attacks on deep neural networks by proposing CAG, a generative model-based attack that achieves at least 500 times speedup, reduces memory cost, and improves robustness and transferability compared to state-of-the-art methods.
Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclassfication by adding imperceptible perturbations to legitimate inputs. Researchers have developed numerous types of adversarial attack methods. However, from the perspective of practical deployment, these methods suffer from several drawbacks such as long attack generating time, high memory cost, insufficient robustness and low transferability. We propose a Content-aware Adversarial Attack Generator (CAG) to achieve real-time, low-cost, enhanced-robustness and high-transferability adversarial attack. First, as a type of generative model-based attack, CAG shows significant speedup (at least 500 times) in generating adversarial examples compared to the state-of-the-art attacks such as PGD and C\&W. CAG only needs a single generative model to perform targeted attack to any targeted class. Because CAG encodes the label information into a trainable embedding layer, it differs from prior generative model-based adversarial attacks that use $n$ different copies of generative models for $n$ different targeted classes. As a result, CAG significantly reduces the required memory cost for generating adversarial examples. CAG can generate adversarial perturbations that focus on the critical areas of input by integrating the class activation maps information in the training process, and hence improve the robustness of CAG attack against the state-of-art adversarial defenses. In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations. Extensive experiments on different datasets and DNN models have verified the real-time, low-cost, enhanced-robustness, and high-transferability benefits of CAG.