ASSC: Adaptively Stochastic Smoothing based Adversarial Robustness Certification of Malware Detection Models

In recent years, the stochastic smoothing technique for adversarial robustness certification of artificial intelligence(AI) models is mainly applied in computer vision domain, with fewer applications in security-related domains such as malware. In the malware detection task, the noisy samples generated by stochastic smoothing algorithms may break the functionality of the malware. As a result, malware may be executable in the real world. In addition, stochastic smoothing-based robustness certification methods of AI detection models may be costly. In this paper, an adaptively stochastic smoothing based approach for adversarial robustness certification of malware detection models, which we call ASSC, is proposed. ASSC constructs a smoothing model by adding discrete Bernoulli noise only to specific constraint positions. Moreover, an adaptive smoothing model is constructed to improve the certification efficiency. Experiments have shown that, our proposed method can at least reduce the time of robustness certification average by 80% on two public datasets, which can significantly reduce the certification runtime. In addition, the experimental results can also prove that, overall, ASSC can guarantee a higher certification accuracy than other methods under the same certification radius.