14 March 2024 in IEEE Transactions on Information Forensics and Security
Secure aggregation becomes a major solution to providing privacy for federated learning. Secure aggregation for mobile devices typically relies on Shamir secret sharing (SSS) to achieve dropout robustness, but limits the system’s corruption and dropout tolerance. Although Prio+, a state-of-the-art method utilizing two non-colluding servers, avoids such limitations, its effectiveness is only against honest-but-curious servers. Thus, this paper presents a novel secure aggregation protocol in the malicious model. The proposed protocol uses a non-colluding server and initiator to achieve almost full (up to n -2) corruption and dropout tolerance, and exploits our discrete-logarithm (DL) extractable and equivocable commitment scheme to achieve malicious security. The proposed protocol’s security is proven in two models: malicious users colluding with the server and malicious users colluding with the initiator. Finally, a prototype of the developed protocol is implemented, with the experimental results demonstrating that our protocol is efficient and suitable for both cross-device and cross-silo federated learning scenarios. Compared with the sum protocol of Prio+, the proposed protocol achieves malicious security with affordable additional overhead, i.e., 4.8 to 6.1 times more computation cost and 2.8 to 2.9 times more communication cost for a single user.
26 March 2020 in Science China Information Sciences
1 January 2015 in International Journal of Grid and Utility Computing
Cloud computing is becoming widely used both in academia and industry and one of the most important applications is delegating computation. A computationally weak client delegates tasks to one or more workers in cloud, and this is called delegation computation. Delegation computation has high security requirements, and it needs to ensure that the information of the client would not be leaked and the computation will be computed correctly. What's more, the clients can verify the result after computation. This paper presents a delegation protocol and it allows the client to delegate a large polynomial to more than one worker while keeping privacy and correctness. In this paper, the workers make computations directly on the shares from the client, and keep the threshold unchanged. This protocol has these advantages: the protocol keeps privacy of the original input; the workers have no interaction with each other during the execution; the protocol keeps the threshold unchanged.
4 March 2025 in IACR Transactions on Cryptographic Hardware and Embedded Systems
Secure aggregation is a popular solution to ensuring privacy for federated learning. However, when considering malicious participants in secure aggregation, it is difficult to achieve both privacy and high efficiency. Therefore, we propose SeaFlame, a communication-efficient secure aggregation protocol against malicious participants. Inspired by the state-of-the-art work, ELSA, SeaFlame also utilizes two non-colluding servers to ensure privacy against malicious entities and provide defenses against boosted gradients. Crucially, to improve communication efficiency, SeaFlame uses arithmetic sharing together with arithmetic-to-arithmetic share conversion to reduce client communication, and uses the random linear combination to reduce server communication.Security analysis proves that our SeaFlame guarantees privacy against malicious clients colluding with one malicious server. Experimental evaluation demonstrates that, compared to ELSA, SeaFlame optimizes communication by up to 10.5, 6.00, and 8.17 times for a client, a server, and all entities, at the expense of 1.25-1.86 times additional end-to-end runtime.