Collaborative Research: SaTC: CORE: Medium: Foundations of Trust-Centered Multi-Agent Distributed Coordination

协作研究：SaTC：核心：媒介：以信任为中心的多智能体分布式协调的基础

• 批准号: 2147631
• 负责人: Andrea Goldsmith
• 金额: $ 20.57万
• 依托单位: Princeton University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-15 至 2026-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2147631&HistoricalAwards=false
• 关键词: Collaborative; Research; SaTC; CORE; Medium

This project will develop the theoretical foundations of trust-centered resilience for distributed coordination and optimization of multi-agent systems in the presence of adversaries. The resilience is to be achieved by agents’ learning trustworthiness of their neighbors through local communications, which allows them to mitigate the detrimental impact of adversarial actions. In particular, the agents can identify and isolate the adversaries and, thus, the agents are able to sustain the desired system performance. Such resilient autonomous multi-agent systems are likely to play an important role in the future deployment of autonomous vehicle fleets, automated delivery systems (such as robots and drones), as well as physical and connected devices in our homes.The approach is to establish the theoretical foundations and analytical framework for efficient exploitation of stochastic "side information" found in the network, in order to arrive at provably stronger guarantees of resilience for multi-agent optimization problems. Malicious actions are addressed through probabilistic link-corruption models, which provides an important separation between the attack and its impact on the system. This separation is critical as it enables the development of trust models using statistical inference techniques. The resulting model is suitable for studying the impact of corrupted data on the resilience of multi-agent coordination and optimization tasks. The focus in this work is on deriving resilient distributed optimization algorithms and resilient consensus protocols that can tolerate more than half of the network connectivity being malicious; a classical requirement that this project aims to relax. Specific objectives of the project are to develop methods for distributed detection of an attack, attack mitigation, and characterization of attainable performance guarantees in the presence of adversaries. The contribution is a unified theory for understanding how inter-agent communications can be used to detect and isolate malicious agents, while provably quantifying their impact on system performance.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目将开发以信任为中心的基础，以在敌人存在下进行多代理茎的分布式协调和优化。对抗性授权的有害影响，代理可以隔离对手和LE，以维持所需的系统性能。我们的房屋。在网络中发现的剥削性方面的理论性建筑框架，在可证明的强大的鸟鸟类的Orrive中。分离是至关重要ECT的旨在放松该项目的特定目标是在贡献中降低攻击的检测。它们对系统性能的影响。该奖项反映了NSF'SF'Story D任务D被认为是值得通过Toundation的知识分子优点和更广泛影响的评论标准来评估的。

项目成果

Resilience to Malicious Activity in Distributed Optimization for Cyberphysical Systems

• DOI: 10.1109/cdc51059.2022.9992416
• 发表时间: 2022-12
• 期刊: 2022 IEEE 61st Conference on Decision and Control (CDC)
• 作者: M. Yemini;A. Nedić;S. Gil;A. Goldsmith

Exploiting Trust for Resilient Hypothesis Testing with Malicious Robots

• DOI: 10.1109/icra48891.2023.10160385
• 发表时间: 2022-09
• 期刊: 2023 IEEE International Conference on Robotics and Automation (ICRA)
• 作者: Matthew Cavorsi;Orhan Eren Akgün;M. Yemini;A. Goldsmith;Stephanie Gil

On Differential Privacy for Wireless Federated Learning with Non-coherent Aggregation

• DOI: 10.1109/globecom54140.2023.10437931
• 发表时间: 2023-12
• 期刊: GLOBECOM 2023 - 2023 IEEE Global Communications Conference
• 作者: Mohamed Seif;Alphan Șahin;H. V. Poor;Andrea J. Goldsmith

Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy

• DOI: 10.1109/isit54713.2023.10206910
• 发表时间: 2023-02
• 期刊: 2023 IEEE International Symposium on Information Theory (ISIT)
• 作者: R. Saha;Mohamed Seif;M. Yemini;A. Goldsmith;H. Poor