arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.08866eess.SP
收藏

规避攻击对基于联邦学习的信号分类器的毒害作用有多大?

How Potent are Evasion Attacks for Poisoning Federated Learning-Based Signal Classifiers?

Su Wang, Rajeev Sahay, Christopher G. Brinton

摘要:

最近人们对利用联邦学习(FL)进行无线电信号分类任务很感兴趣。在FL中,模型参数定期从参与设备(在其自己的本地数据集上进行训练)传送到中央服务器,该中央服务器将它们聚合成全局模型。虽然FL具有隐私/安全优势,因为原始数据不会离开设备,但它仍然容易受到一些对抗性攻击。在这项工作中,我们揭示了基于FL的信号分类器对模型中毒攻击的敏感性,尽管没有观察到数据传输,但这种攻击会损害训练过程。在这种能力下,我们开发了一个攻击框架,在该框架中,受损的FL设备使用对抗性规避攻击来扰乱其本地数据集。结果,全局模型的训练过程在分布内信号上显著降级(即,在每个边缘设备处具有相同分布的信道上接收的信号)。我们将我们的工作与先前提出的FL攻击进行比较,并揭示在我们的攻击框架下,只有一个对抗设备以低功率扰动运行,就可以对全局分类器进行有效的模型中毒攻击。此外,我们发现,更多的设备参与对抗中毒将成比例地降低分类性能。

英文摘要:

There has been recent interest in leveraging federated learning (FL) for radio signal classification tasks. In FL, model parameters are periodically communicated from participating devices, training on their own local datasets, to a central server which aggregates them into a global model. While FL has privacy/security advantages due to raw data not leaving the devices, it is still susceptible to several adversarial attacks. In this work, we reveal the susceptibility of FL-based signal classifiers to model poisoning attacks, which compromise the training process despite not observing data transmissions. In this capacity, we develop an attack framework in which compromised FL devices perturb their local datasets using adversarial evasion attacks. As a result, the training process of the global model significantly degrades on in-distribution signals (i.e., signals received over channels with identical distributions at each edge device). We compare our work to previously proposed FL attacks and reveal that as few as one adversarial device operating with a low-powered perturbation under our attack framework can induce the potent model poisoning attack to the global classifier. Moreover, we find that more devices partaking in adversarial poisoning will proportionally degrade the classification performance.

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。

↑