SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing defenses either incur impractical computational overhead for embedded platforms or fail to achieve privacy protection and good model utility at the same time. Moreover, many defenses can be easily bypassed by adaptive adversaries who have obtained the defense details. To address these limitations, we propose SVDefense, a novel defense framework against GIAs that leverages the truncated Singular Value Decomposition (SVD) to obfuscate gradient updates. SVDefense introduces three key innovations, a Self-Adaptive Energy Threshold that adapts to client vulnerability, a Channel-Wise Weighted Approximation that selectively preserves essential gradient information for effective model training while enhancing privacy protection, and a Layer-Wise Weighted Aggregation for effective model aggregation under class imbalance. Our extensive evaluation shows that SVDefense outperforms existing defenses across multiple applications, including image classification, human activity recognition, and keyword spotting, by offering robust privacy protection with minimal impact on model accuracy. Furthermore, SVDefense is practical for deployment on various resource-constrained embedded platforms. We will make our code publicly available upon paper acceptance.
Code (0)
등록된 구현이 없습니다.
Tasks
Human Activity RecognitionImage ClassificationFederated LearningKeyword SpottingSimilar Papers 제목 키워드 기반
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private dat…
Federated LearningEvaluating Gradient Inversion Attacks and Defenses in Federated Learning
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recove…
Federated LearningEnhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation
Federated learning (FL) is a privacy-enhanced distributed machine learning framework, in which multiple clients collaboratively train a global model by exchanging their model updates without sharing local private dat…
Federated LearningGet your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT data
The past decade has seen a rapid adoption of Artificial Intelligence (AI), specifically the deep learning networks, in Internet of Medical Things (IoMT) ecosystem. However, it has been shown recently that the deep learni…
Medical DiagnosisDefending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses an…
Federated LearningPrivacy Preserving