发现安全聚合协议漏洞，攻击者可利用可预测掩码泄露用户隐私。
Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
- 发现MicroSecAgg协议中掩码值可预测，导致隐私保护失效
- 攻击者通过分析训练迭代中的掩码模式，成功还原用户数据
- 适合关注联邦学习安全、隐私保护的研究者和开发者
联邦学习允许多方在本地数据上协同训练全局模型，避免数据集中传输。然而，用户训练更新可能被攻击者利用，泄露数据隐私。安全聚合协议通过加密用户更新并让服务器聚合，以保护隐私。MicroSecAgg（PoPETS 2024）提出一种单服务器方案，通过一次性设置密钥并在多轮训练中复用，降低通信开销。本文揭示该协议存在安全缺陷：其掩码值具有可预测性，使攻击者能通过分析多次迭代中的更新，推断出原始用户数据。我们详细描述了该漏洞及攻击方法，并强调需采用动态、不可预测的掩码策略来增强安全性。同时提出潜在防御措施，确保安全聚合框架的隐私保护能力。
原文摘要 · Abstract (English)
Federated learning enables the collaborative learning of a global model on diverse data, preserving data locality and eliminating the need to transfer user data to a central server. However, data privacy remains vulnerable, as attacks can target user training data by exploiting the updates sent by users during each learning iteration. Secure aggregation protocols are designed to mask/encrypt user updates and enable a central server to aggregate the masked information. MicroSecAgg (PoPETS 2024) proposes a single server secure aggregation protocol that aims to mitigate the high communication complexity of the existing approaches by enabling a one-time setup of the secret to be re-used in multiple training iterations. In this paper, we identify a security flaw in the MicroSecAgg that undermines its privacy guarantees. We detail the security flaw and our attack, demonstrating how an adversary can exploit predictable masking values to compromise user privacy. Our findings highlight the critical need for enhanced security measures in secure aggregation protocols, particularly the implementation of dynamic and unpredictable masking strategies. We propose potential countermeasures to mitigate these vulnerabilities and ensure robust privacy protection in the secure aggregation frameworks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。