arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.13849cs.CR
收藏

说话人识别中样本无关的联邦学习后门攻击

Sample-Independent Federated Learning Backdoor Attack in Speaker Recognition

Weida Xu, Yang Xu, Sicong Zhang

AI总结:

本文提出 GhostB,一种不修改样本、不依赖 dropout 的说话人识别联邦学习后门攻击方法,利用特定神经元值作为触发器,在多个数据集上实现 100% 激活成功率,并分析了神经元分散程度和深度对攻击效果的影响。

摘要:

在联邦学习中,后门攻击通过在对抗性客户端的数据中嵌入触发器,从而向模型中注入后门。为了增强隐蔽性,已有研究提出一种基于 dropout 层、无需修改样本即可植入后门的攻击方法。然而,这些方法难以在评估模式下隐蔽地利用 dropout,因而阻碍了其在真实场景中的部署。针对上述问题,本文提出 GhostB,这是一种面向说话人识别的新型联邦学习后门攻击方法,既不修改样本,也不依赖 dropout。该方法利用神经元产生特定值的行为作为触发器。通过将这些神经元值映射到攻击者指定的类别,当在指定神经元上检测到特定特征值时,后门即被植入并激活。我们在 TIMIT、LibriSpeech 和 VoxCeleb2 数据库上,在闭集识别(CSI)和开集识别(OSI)两种场景下进行的实验表明,GhostB 在说话人识别中激活后达到 100% 的成功率,并且在涉及 1 到 50 个幽灵神经元的实验中均保持该成功率。本文还研究了神经元的分散程度及其在隐藏层中的深度对成功率的影响,结果表明,神经元分散程度和位置的增加会显著降低攻击效果,甚至可能导致攻击失败。

英文摘要:

In federated learning, backdoor attacks embed triggers in the adversarial client's data to inject a backdoor into the model. In order to enhance the stealth, an attack method based on the dropout layer has been proposed, which can implant the backdoor without modifying the sample. However, these methods struggle to covertly utilize dropout in evaluation mode, thus hindering their deployment in real-world scenarios. To address these, this paper introduces GhostB, a novel approach to federated learning backdoor attacks in speaker recognition that neither alters samples nor relies on dropout. This method employs the behavior of neurons producing specific values as triggers. By mapping these neuronal values to categories specified by the adversary, the backdoor is implanted and activated when particular feature values are detected at designated neurons. Our experiments conducted on TIMIT, LibriSpeech, and VoxCeleb2 databases in both Closed Set Identification (CSI) and Open Set Identification (OSI) scenarios demonstrate that GhostB achieves a 100% success rate upon activation in speaker recognition, with this rate maintained across experiments involving 1 to 50 ghost neurons. This paper investigates how the dispersion of neurons and their depth within hidden layers affect the success rate, revealing that increased dispersion and positioning of neurons can significantly decrease effectiveness, potentially rendering the attack unsuccessful.

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。

↑