extit{FLARE}: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning

2025-11-18

AI Summary

Federated learning is vulnerable to Byzantine attacks and data poisoning by malicious clients; existing defenses rely on static thresholds and binary decisions, failing to adapt to dynamic, adaptive threats. This paper proposes an adaptive multi-dimensional reputation framework that models client trustworthiness as a continuous, multi-dimensional score. It integrates self-calibrating thresholds, reputation-weighted soft-exclusion aggregation, and local differential privacy–protected reputation computation. To rigorously evaluate robustness, we innovatively design Statistical Mimicry (SM)—a high-stealth attack serving as a challenging benchmark. Extensive experiments on MNIST, CIFAR-10, and SVHN demonstrate that our method outperforms state-of-the-art approaches: it improves model accuracy, accelerates convergence, enhances attack resilience by 16%, and maintains stable convergence even under 30% non-malicious-but-non-IID baselines. Moreover, it achieves superior detection performance with low communication and computational overhead.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who compromise model integrity through Byzantine attacks, data poisoning, or adaptive adversarial behaviors. Existing defense mechanisms rely on static thresholds and binary classification, failing to adapt to evolving client behaviors in real-world deployments. We propose FLARE, an adaptive reputation-based framework that transforms client reliability assessment from binary decisions to a continuous, multi-dimensional trust evaluation. FLARE integrates: (i) a multi-dimensional reputation score capturing performance consistency, statistical anomaly indicators, and temporal behavior, (ii) a self-calibrating adaptive threshold mechanism that adjusts security strictness based on model convergence and recent attack intensity, (iii) reputation-weighted aggregation with soft exclusion to proportionally limit suspicious contributions rather than eliminating clients outright, and (iv) a Local Differential Privacy (LDP) mechanism enabling reputation scoring on privatized client updates. We further introduce a highly evasive Statistical Mimicry (SM) attack, a benchmark adversary that blends honest gradients with synthetic perturbations and persistent drift to remain undetected by traditional filters. Extensive experiments with 100 clients on MNIST, CIFAR-10, and SVHN demonstrate that FLARE maintains high model accuracy and converges faster than state-of-the-art Byzantine-robust methods under diverse attack types, including label flipping, gradient scaling, adaptive attacks, ALIE, and SM. FLARE improves robustness by up to 16% and preserves model convergence within 30% of the non-attacked baseline, while achieving strong malicious-client detection performance with minimal computational overhead. https://github.com/Anonymous0-0paper/FLARE

Problem

• Addresses vulnerability of federated learning to malicious client attacks
• Replaces binary reliability assessment with continuous multi-dimensional trust evaluation
• Introduces adaptive reputation framework to maintain model accuracy under attacks

Innovation

• Multi-dimensional reputation score for continuous trust evaluation
• Self-calibrating adaptive threshold mechanism for dynamic security
• Reputation-weighted aggregation with soft exclusion of suspicious clients