arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.10752cs.LGcs.AIcs.CR
收藏

分层联邦深度学习的安全评估

Security Assessment of Hierarchical Federated Deep Learning

Newcastle University(纽卡斯尔大学);Alahsa Technical College(艾拉哈萨技术学院);University of Catania(卡塔尼亚大学);Technical University of Ostrava(俄斯特拉发技术大学)

D Alqattan, R Sun, H Liang, G Nicosia, V Snasel, R Ranjan, V Ojha

AI总结:

本研究评估分层联邦学习(HFL)的安全性,发现其对非目标训练时攻击鲁棒,但易受后门攻击,且分层聚合增强了对推理时攻击的抵抗力。

摘要:

分层联邦学习(HFL)是一种有前景的分布式深度学习模型训练范式,但它存在由对抗性攻击引发的关键安全问题。本研究采用一种新颖的方法,通过关注其对推理时和训练时对抗性攻击的鲁棒性,来调查并评估HFL的安全性。通过在多种数据集和攻击场景下进行一系列广泛实验,我们发现,由于其分层结构,HFL对非目标训练时攻击表现出鲁棒性。然而,目标攻击,特别是后门攻击,会利用这种架构,尤其是当恶意客户端位于边缘服务器的重叠覆盖区域时。因此,HFL在其鲁棒性上表现出双重性,展示了其从攻击中恢复的能力,这得益于其分层聚合,增强了其对对抗训练的适用性,从而加强了对推理时攻击的抵抗力。这些见解强调了在HFL系统中采取平衡安全策略的必要性,即利用其固有优势,同时有效缓解漏洞。

英文摘要:

Hierarchical federated learning (HFL) is a promising distributed deep learning model training paradigm, but it has crucial security concerns arising from adversarial attacks. This research investigates and assesses the security of HFL using a novel methodology by focusing on its resilience against adversarial attacks inference-time and training-time. Through a series of extensive experiments across diverse datasets and attack scenarios, we uncover that HFL demonstrates robustness against untargeted training-time attacks due to its hierarchical structure. However, targeted attacks, particularly backdoor attacks, exploit this architecture, especially when malicious clients are positioned in the overlapping coverage areas of edge servers. Consequently, HFL shows a dual nature in its resilience, showcasing its capability to recover from attacks thanks to its hierarchical aggregation that strengthens its suitability for adversarial training, thereby reinforcing its resistance against inference-time attacks. These insights underscore the necessity for balanced security strategies in HFL systems, leveraging their inherent strengths while effectively mitigating vulnerabilities.

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。

↑