arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.00918cs.CR
收藏

基于DNN的无线通信系统的鲁棒对抗攻击

Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems

Alireza Bahramali, Milad Nasr, Amir Houmansadr, Dennis Goeckel, Don Towsley

摘要:

深度神经网络(DNN)由于其有前途的性能而在无线通信系统中变得流行。然而,与其他基于DNN的应用程序类似,它们容易受到对抗性示例的影响。在这项工作中,我们提出了一个输入不可知的,不可检测的,和强大的对抗攻击对基于DNN的无线通信系统在白盒和黑盒的情况下。我们设计了量身定制的通用对抗扰动(UAP)来执行攻击。我们还使用生成对抗网络(GAN)来为我们的攻击实施不可检测性约束。此外,我们调查我们的攻击对抗对策的鲁棒性。我们表明,在通信方部署的防御机制的存在下,我们的攻击比现有的针对基于DNN的无线系统的攻击表现得更好。特别是,结果表明,即使采用经过深思熟虑的防御措施,基于DNN的无线通信也容易受到对抗攻击的攻击。

英文摘要:

Deep Neural Networks (DNNs) have become prevalent in wireless communication systems due to their promising performance. However, similar to other DNN-based applications, they are vulnerable to adversarial examples. In this work, we propose an input-agnostic, undetectable, and robust adversarial attack against DNN-based wireless communication systems in both white-box and black-box scenarios. We design tailored Universal Adversarial Perturbations (UAPs) to perform the attack. We also use a Generative Adversarial Network (GAN) to enforce an undetectability constraint for our attack. Furthermore, we investigate the robustness of our attack against countermeasures. We show that in the presence of defense mechanisms deployed by the communicating parties, our attack performs significantly better compared to existing attacks against DNN-based wireless systems. In particular, the results demonstrate that even when employing well-considered defenses, DNN-based wireless communications are vulnerable to adversarial attacks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑