CAREER: Building Reliable Network of Unreliable Things

近年来见证了物联网（IoT）的兴起，这是一种新兴的网络范式，通过无处不在的传感、计算和通信设备将人类和物理世界连接起来。该项目的最终目标是构建可靠、健壮和安全的物联网系统，这些系统通常由大量不可靠的无线设备组成，有时甚至由恶意用户携带。该项目开发了TRIP，这是一个物联网系统的真相发现、激励和隐私保护机制的三合一集成框架。该框架包括：1)从无处不在的物联网设备产生的海量感官数据中提取真实信息的真相发现机制；2)既能保护用户隐私又能抵御恶意攻击的安全和隐私机制；3)选择可靠参与者以最大限度提高收集信息质量的激励机制。该项目首次系统地研究了物联网系统的集成设计，其成功完成不仅将促进具有重大自然和社会影响的整个应用范围，而且还将促进各种课程开发和推广活动，使大量学生，特别是女性和少数民族学生受益。为了实现所提出的TRIP系统，本项目解决了一系列重要的研究挑战。首先，为了从人类携带的物联网设备收集的嘈杂和稀疏的感官数据中推断出真值信息，该项目提供了一种新的真值发现方法，可以捕获不同用户的可靠性变化以及对象之间的相关性。其次，该项目不仅研究了允许服务器在不知道用户观察的真正价值的情况下进行真相发现操作的隐私保护机制，还研究了防御恶意用户试图注入虚假信息以破坏或经济奖励的安全解决方案。第三，建立有效的激励机制，激励可靠的用户为物联网任务做出贡献。最后，将上述机制以分布式和并行的方式无缝集成到联网物联网系统中，并在真实的测试平台上进行评估，以验证所提出研究的有效性、效率和实用性。

Recent years have witnessed the rise of Internet of Things (IoT), a newly emergent networking paradigm that connects humans and the physical world through ubiquitous sensing, computing, and communicating devices. With the ultimate goal of building reliable, robust, and secure IoT systems that are usually composed of multitudes of unreliable wireless devices - sometimes even carried by malicious users - this project develops TRIP, a 3-in-1 integrated framework of TRuth discovery, Incentive, and Privacy preserving mechanisms for IoT systems. This framework consists of 1) a truth discovery mechanism that can distill true information from the deluge of sensory data generated by the ubiquitous IoT devices, 2) a security and privacy mechanism that can not only protect user privacy but also defend against malicious attack, and 3) an incentive mechanism that can select reliable participants in order to maximize the quality of collected information. The successful completion of this project, which for the first time systematically investigates an integrated design of IoT systems, will facilitate not only a whole spectrum of applications that have significant natural and societal impact, but also various curriculum development and outreach activities that can benefit a large group of students, especially the female and minority students.In order to realize the proposed TRIP system, this project addresses a series of important research challenges. First, to infer truth information from the noisy and sparse sensory data collected by human-carried IoT devices, this project delivers a novel truth discovery method that can capture the variety in the reliability of different users as well as the correlations among the objects. Second, this project investigates not only privacy preserving mechanisms that allow the server to conduct truth discovery operations without knowing the genuine values of user observations, but also security solutions that defend against malicious users who try to inject false information for the purpose of sabotage or financial rewards. Third, an effective incentive mechanism is developed to motivate reliable users to contribute to the IoT tasks. Finally, the above mechanisms are seamlessly integrated into networked IoT systems in a distributed and parallel manner, and evaluated on real testbeds in order to validate the effectiveness, efficiency, and the practicality of the proposed research.