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 2403.18607cs.CRcs.AIeess.SP
收藏

Spikewhisper:针对低功耗设备上联邦神经形态学习的时序脉冲后门攻击

Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices

Shanghai Jiao Tong University(上海交通大学);Hong Kong Polytechnic University(香港理工大学);North Carolina State University(北卡罗来纳州立大学)

Hanqing Fu, Gaolei Li, Jun Wu, Jianhua Li, Xi Lin, Kai Zhou, Yuchen Liu

AI总结:

本文提出针对联邦神经形态学习的时序脉冲后门攻击Spikewhisper,利用时分复用概念使恶意客户端在不同时间片注入局部触发器,实验证明其攻击成功率高于时间集中式攻击且对触发器持续时间敏感。

摘要:

联邦神经形态学习(FedNL)利用事件驱动的脉冲神经网络和联邦学习框架,在大量分布式低功耗设备上有效执行智能分析任务,但也表现出对中毒攻击的脆弱性。传统深度神经网络后门攻击的威胁通常来自时不变数据。然而,在FedNL中,未知威胁可能隐藏在时变的脉冲信号中。本文开始利用时分复用的概念探索FedNL系统的一种新漏洞,称为Spikewhisper,它允许攻击者尽可能逃避检测,因为多个恶意客户端可以在不同时间片以不同触发器隐蔽地进行中毒。具体而言,Spikewhisper的隐蔽性源于全局触发器的时域可分性,其中每个恶意客户端仅将一个局部触发器粘贴到神经形态样本的某个时间片,并且每个局部触发器的极性和运动可由攻击者配置。基于两个不同神经形态数据集的大量实验表明,Spikewispher的攻击成功率高于时间集中式攻击。此外,验证了Spikewispher的效果对触发器持续时间敏感。

英文摘要:

Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks. The threat of backdoor attacks on traditional deep neural networks typically comes from time-invariant data. However, in FedNL, unknown threats may be hidden in time-varying spike signals. In this paper, we start to explore a novel vulnerability of FedNL-based systems with the concept of time division multiplexing, termed Spikewhisper, which allows attackers to evade detection as much as possible, as multiple malicious clients can imperceptibly poison with different triggers at different timeslices. In particular, the stealthiness of Spikewhisper is derived from the time-domain divisibility of global triggers, in which each malicious client pastes only one local trigger to a certain timeslice in the neuromorphic sample, and also the polarity and motion of each local trigger can be configured by attackers. Extensive experiments based on two different neuromorphic datasets demonstrate that the attack success rate of Spikewispher is higher than the temporally centralized attacks. Besides, it is validated that the effect of Spikewispher is sensitive to the trigger duration.

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。

↑