arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02605cs.CRcs.AIcs.CVcs.LG
收藏

针对联邦学习中投毒攻击的新型防御:结合自编码器的LayerCAM

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder

CyLab Security and Privacy Institute, Carnegie Mellon University(卡内基梅隆大学CyLab安全与隐私研究所);Real-Time and Embedded Computing Systems Research Centre (CISTER)(实时与嵌入式计算系统研究中心(CISTER));Commonwealth Scientific and Industrial Research Organization (CSIRO)(英联邦科学与工业研究组织(CSIRO));University of Cambridge(剑桥大学);Alan Turing Institute(阿兰·图灵研究所)

Jingjing Zheng, Xin Yuan, Kai Li, Wei Ni, Eduardo Tovar, Jon Crowcroft

AI总结:

针对联邦学习中规避欧氏距离检测的投毒攻击,本文提出LayerCAM-AE防御策略。该方法结合层类激活映射与自编码器生成并处理模型更新热力图以识别异常,并引入投票算法降低误分类风险。实验表明该策略在IID和非IID设置下均实现了完美的检测率与测试准确率,显著优于现有防御模型。

摘要:

针对联邦学习(FL)的近期攻击可以通过引入恶意模型更新来规避广泛采用的基于欧几里得距离的检测方法。本文提出了一种新型防御策略,称为LayerCAM-AE,旨在对抗联邦学习中的模型投毒。LayerCAM-AE提出了一种新的层类激活映射(LayerCAM)与自编码器(AE)相集成的方法,显著增强了检测能力。具体而言,LayerCAM-AE为每个本地模型更新生成热力图,随后将其转换为更紧凑的视觉格式。自编码器旨在处理来自本地模型更新的LayerCAM热力图,提升其独特性,从而提高识别异常图和恶意本地模型的准确率。为应对LayerCAM-AE的误分类风险,开发了一种投票算法,若某本地模型更新的热力图在多轮通信中持续表现可疑,则将其标记为恶意。在独立同分布(IID)和非IID设置下,将LayerCAM-AE在SVHN和CIFAR-100数据集上与现有的ResNet-50和REGNETY-800MF防御模型进行了广泛测试。实验结果表明,LayerCAM-AE提高了检测率(Recall: 1.0, Precision: 1.0, FPR: 0.0, Accuracy: 1.0, F1 score: 1.0, AUC: 1.0)及FL中的测试准确率,超越了ResNet-50和REGNETY-800MF的性能。summary_cn

英文摘要:

Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as LayerCAM-AE, designed to counteract model poisoning in federated learning. The LayerCAM-AE puts forth a new Layer Class Activation Mapping (LayerCAM) integrated with an autoencoder (AE), significantly enhancing detection capabilities. Specifically, LayerCAM-AE generates a heat map for each local model update, which is then transformed into a more compact visual format. The autoencoder is designed to process the LayerCAM heat maps from the local model updates, improving their distinctiveness and thereby increasing the accuracy in spotting anomalous maps and malicious local models. To address the risk of misclassifications with LayerCAM-AE, a voting algorithm is developed, where a local model update is flagged as malicious if its heat maps are consistently suspicious over several rounds of communication. Extensive tests of LayerCAM-AE on the SVHN and CIFAR-100 datasets are performed under both Independent and Identically Distributed (IID) and non-IID settings in comparison with existing ResNet-50 and REGNETY-800MF defense models. Experimental results show that LayerCAM-AE increases detection rates (Recall: 1.0, Precision: 1.0, FPR: 0.0, Accuracy: 1.0, F1 score: 1.0, AUC: 1.0) and test accuracy in FL, surpassing the performance of both the ResNet-50 and REGNETY-800MF. Our code is available at: https://github.com/jjzgeeks/LayerCAM-AE

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。

↑