维护联邦学习中的鲁棒性：趋势、新兴策略与研究机遇
Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities
- BITS Pilani Dubai Campus（BITS Pilani迪拜校区）
- University of Palermo（巴勒莫大学）
- Missouri University of Science and Technology（密苏里科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文从威胁、聚合策略和防御策略三个角度综合综述联邦学习的鲁棒性，分类攻击面与防御方法，并评估现有实践，指出开放挑战以指导未来研究。
AI中文摘要：
尽管联邦学习（FL）在机器学习中已被广泛用于保护用户隐私，但它仍然面临各种鲁棒性挑战，包括性能受损风险、信息窃取威胁和聚合漏洞。这项工作从三个紧密关联的角度对联邦学习鲁棒性进行了整体综合：（i）以威胁为中心的鲁棒性视角，对多方面的攻击面进行分类；（ii）一个结构化的鲁棒聚合策略分类法，区分以结果为中心的方法与以安全为中心的策略；（iii）一个分层防御策略分类法。我们严格审视了当前联邦学习鲁棒性的评估实践，并确定了主要应用和开放研究挑战，以指导未来研究。
英文摘要：
While Federated Learning (FL) has been widely adopted for protecting user privacy in machine learning, it remains vulnerable to various robustness challenges, including performance-impairment risks, information-stealing threats, and aggregation vulnerabilities. This work offers a holistic synthesis of FL robustness along three tightly coupled angles: (i) a threat-centric view of robustness that categorizes the multifaceted attack surfaces, (ii) a structured taxonomy of robust aggregation strategies distinguishing outcome-centric approaches from security-centric strategies, and (iii) a layered taxonomy of defensive strategies. We rigorously examine current evaluation practices for FL robustness and identify major applications and open research challenges to guide future research.
