差别隐私
计算机科学
联合学习
协议(科学)
可扩展性
人气
计算机安全
私人信息检索
推论
人工智能
数据挖掘
数据库
医学
心理学
社会心理学
替代医学
病理
作者
M.A.P. Chamikara,Dongxi Liu,Seyit Camtepe,Surya Nepal,Marthie Grobler,Péter Bertök,Ibrahim Khalil
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:2
标识
DOI:10.48550/arxiv.2202.06053
摘要
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially private (DP) solutions. However, DP approaches assume that the FL server (that aggregates the models) is honest (run the FL protocol honestly) or semi-honest (run the FL protocol honestly while also trying to learn as much information as possible). These assumptions make such approaches unrealistic and unreliable for real-world settings. Besides, in real-world industrial environments (e.g., healthcare), the distributed entities (e.g., hospitals) are already composed of locally running machine learning models (this setting is also referred to as the cross-silo setting). Existing approaches do not provide a scalable mechanism for privacy-preserving FL to be utilized under such settings, potentially with untrusted parties. This paper proposes a new local differentially private FL (named LDPFL) protocol for industrial settings. LDPFL can run in industrial settings with untrusted entities while enforcing stronger privacy guarantees than existing approaches. LDPFL shows high FL model performance (up to 98%) under small privacy budgets (e.g., epsilon = 0.5) in comparison to existing methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI