SAFELearning：在联邦学习的安全聚合中实现后门可检测性
SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation
AI总结：
本文提出SAFELearning框架，通过遗忘随机分组和部分参数披露两个新原语，在联邦学习的安全聚合中实现后门检测，显著降低后门模型准确率且不损害主任务，同时具备高效性和鲁棒性。
摘要：
为了保护模型隐私，联邦学习中的本地模型参数在发送给远程聚合器之前应当被混淆。这种技术被称为安全聚合（secure aggregation）。然而，考虑到现有的异常检测方法大多需要访问明文本地模型，安全聚合使得模型投毒攻击（如后门攻击）变得更加便利。本文提出了支持安全聚合后门检测的SAFELearning。我们通过两个新原语——遗忘随机分组（ORG）和部分参数披露（PPD）来实现这一点。ORG将参与者划分为一次性随机子组，且组配置对参与者是遗忘的；PPD允许安全地部分披露聚合的子组模型以进行异常检测，而不泄露单个模型隐私。在常见的后门策略下，SAFELearning能够显著降低后门模型准确率，同时不损害主任务准确率。大量实验表明，SAFELearning对恶意和故障参与者具有鲁棒性，同时在通信和计算成本方面比最先进的安全聚合协议更高效。
英文摘要：
For model privacy, local model parameters in federated learning shall be obfuscated before sent to the remote aggregator. This technique is referred to as \emph{secure aggregation}. However, secure aggregation makes model poisoning attacks such backdooring more convenient considering that existing anomaly detection methods mostly require access to plaintext local models. This paper proposes SAFELearning which supports backdoor detection for secure aggregation. We achieve this through two new primitives - \emph{oblivious random grouping (ORG)} and \emph{partial parameter disclosure (PPD)}. ORG partitions participants into one-time random subgroups with group configurations oblivious to participants; PPD allows secure partial disclosure of aggregated subgroup models for anomaly detection without leaking individual model privacy. SAFELearning can significantly reduce backdoor model accuracy without jeopardizing the main task accuracy under common backdoor strategies. Extensive experiments show SAFELearning is robust against malicious and faulty participants, whilst being more efficient than the state-of-art secure aggregation protocol in terms of both communication and computation costs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
