4 March 2019 in IEEE Transactions on Automatic Control
Average consensus underpins key functionalities of distributed systems ranging from distributed information fusion, decision-making, distributed optimization, to load balancing and decentralized control. Existing distributed average consensus algorithms require each node to exchange and disclose state information to its neighbors, which is undesirable in cases where the state is private or contains sensitive information. In this paper, we propose a novel approach that avoids disclosing individual state information in average consensus by letting each node decompose its state into two sub-states. For each node, one of the two sub-states involves in computation and inter-node interactions as if it were the original state, while the other substate interacts only with the first sub-state of the same node, being completely invisible to other nodes. The initial values of the two sub-states are chosen randomly but with their mean fixed to the initial value of the original state, which is key to guarantee convergence to the desired consensus value. In direct contrast to differential-privacy based privacy-preserving average-consensus approaches which enable privacy by compromising accuracy in the consensus value, the proposed approach can guarantee convergence to the exact desired value without any error. Not only is the proposed approach able to prevent the disclosure of a node's initial state to honest-but-curious neighbors, it can also provide protection against inference by external eavesdroppers able to wiretap communication links. Numerical simulations demonstrate the effectiveness of the approach and its advantages over state-of-the-art counterparts.
4 January 2019 in IEEE Transactions on Automatic Control
22 June 2023 in IEEE Transactions on Intelligent Transportation Systems
On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic traffic where the communication topology could be time-varying. Parameter sharing and local rewards are exploited to foster inter-agent cooperation while achieving great scalability. An action masking scheme is employed to improve learning efficiency by filtering out invalid/unsafe actions at each step. In addition, a novel priority-based safety supervisor is developed to significantly reduce collision rate and greatly expedite the training process. A gym-like simulation environment is developed and open-sourced with three different levels of traffic densities. We exploit curriculum learning to efficiently learn harder tasks from trained models under simpler settings. Comprehensive experimental results show the proposed MARL framework consistently outperforms several state-of-the-art benchmarks.
12 July 2018 in IEEE Transactions on Information Forensics and Security
Privacy preservation is addressed for decentralized optimization, where $N$ agents cooperatively minimize the sum of $N$ convex functions private to these individual agents. In most existing decentralized optimization approaches, participating agents exchange and disclose states explicitly, which may not be desirable when the states contain sensitive information of individual agents. The problem is more acute when adversaries exist which try to steal information from other participating agents. To address this issue, we propose a privacy-preserving decentralized optimization approach based on alternating direction method of multipliers (ADMM) and partially homomorphic cryptography. To the best of our knowledge, this is the first time that cryptographic techniques are incorporated in a fully decentralized setting to enable privacy preservation in decentralized optimization in the absence of any third party or aggregator. To facilitate the incorporation of encryption in a fully decentralized manner, we introduce a new ADMM, which allows time-varying penalty matrices and rigorously prove that it has a convergence rate of $O(1/t)$ . Numerical and experimental results confirm the effectiveness and low-computational complexity of the proposed approach.
4 May 2023 in IEEE Transactions on Automatic Control
Decentralized optimization is gaining increased traction due to its widespread applications in large-scale machine learning and multiagent systems. The same mechanism that enables its success, i.e., information sharing among participating agents, however, also leads to the disclosure of individual agents' private information, which is unacceptable when sensitive data are involved. As differential privacy is becoming a de facto standard for privacy preservation, recently results have emerged integrating differential privacy with distributed optimization. However, directly incorporating differential privacy design in existing distributed optimization approaches significantly compromises optimization accuracy. In this article, we propose to redesign and tailor gradient methods for differentially private distributed optimization, and propose two differential-privacy oriented gradient methods that can ensure both rigorous $\epsilon$ -differential privacy and optimality. The first algorithm is based on static-consensus-based gradient methods, and the second algorithm is based on dynamic-consensus (gradient-tracking) based distributed optimization methods and, hence, is applicable to general directed interaction graph topologies. Both algorithms can simultaneously ensure almost sure convergence to an optimal solution and a finite privacy budget, even when the number of iterations goes to infinity. To the best of authors' knowledge, this is the first time that both goals are achieved simultaneously. Numerical simulations using a distributed estimation problem and experimental results on a benchmark dataset confirm the effectiveness of the proposed approaches.
1 October 2018 in IEEE Transactions on Control of Network Systems
Decentralized optimization is crucial for the design, deployment, and functionality of many distributed systems. In this paper, we address the problem of privacy-preservation in decentralized optimization. In most existing decentralized optimization approaches, participating agents exchange and disclose intermediate estimate values to neighboring agents explicitly, which may not be desirable when the estimates contain sensitive information of individual agents. The problem is more acute when adversaries exist which try to steal information from other participating agents. To address this issue, we propose a novel approach that enables privacy-preservation in decentralized optimization by combining partially homomorphic cryptography with the unique properties of the decentralized optimization. We show that cryptographic techniques can be incorporated in a fully decentralized manner to enable privacy-preservation in decentralized optimization in the absence of any third party or aggregator. This is significant in that to our knowledge, all existing cryptographic-based optimization approaches rely on the assistance of a third-party or aggregator in order to protect the privacy of all parties. The approach is also applicable to the average consensus problem, which is finding broad applications in fields as diverse as robotic networks, distributed computing, and power systems. Numerical simulations confirm the effectiveness and low computational complexity of the proposed approach.