Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
This addresses a practical problem for real-world classification systems with hundreds or thousands of categories, representing a novel advancement in adversarial attack methods.
The paper tackles the limitation of existing generation-based adversarial attack methods, which can only target one specific category, by proposing the first Multi-target Adversarial Network (MAN) that generates adversarial samples for any category within a model, achieving stronger attack results and better transferability than state-of-the-art methods.
Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods.