Boosting Adversarial Attacks on Neural Networks with Better Optimizer
This work provides an incremental improvement in adversarial attack success rates, which is important for researchers evaluating the robustness of deep learning models against security threats.
This paper addresses the vulnerability of convolutional neural networks to adversarial examples by proposing a new method that combines a modified Adam optimizer with an iterative gradient-based attack. This approach achieved a state-of-the-art attack success rate of 95.0% on defense models on ImageNet.
Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems. Sophisticated adversarial examples with strong attack performance can also be used as a tool to evaluate the robustness of a model. However, the success rate of adversarial attacks can be further improved in black-box environments. Therefore, this study combines a modified Adam gradient descent algorithm with the iterative gradient-based attack method. The proposed Adam Iterative Fast Gradient Method is then used to improve the transferability of adversarial examples. Extensive experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. By extending our method, we achieved a state-of-the-art attack success rate of 95.0% on defense models.