报告人：Prof. Yingying (Jennifer) Chen，Fellow of National Academy of Inventors (NAI)，ACM Fellow, IEEE Fellow, AAIA Fellow，Department Chair,Electrical and Computer Engineering，Rutgers University(罗格斯大学)

报告时间：2024年05月16日 (星期四) 21:00-22:00 pm

报告地点：腾讯在线会议 520-342-555

报告摘要: The pervasive usage of edge devices such as IoT devices, smartphones, AR/VR headsets, delivery drones, and autonomous vehicles, has experienced a notable upward trend. This trend offers unprecedented opportunities for on-device intelligence and a wide range of edge sensing and computing applications. Artificial Intelligence (AI) has emerged as a key enabler enhancing the efficiency of these emerging applications, including AR/VR applications, intelligent audio assistant systems, and behavior-based user authentication. However, the increasing reliance on AI also introduces inherent security vulnerabilities, which pose significant threats when deploying these applications in real-world environments. This talk aims to discuss recent advancements in AI-enabled edge sensing and computing achieved through hardware-software co-design and on-device AI, highlighting their significant contributions to achieving efficient inference. Additionally, it will delve into the exploration of new attack surfaces, such as adversarial attacks and backdoor attacks, that arise with the integration of AI. Case studies of AR/VR applications and intelligent edge-based audio systems will be presented to illustrate these concepts. Furthermore, the talk will explore novel opportunities, such as domain invariant modeling, which leverage AI to enhance efficiency and bolster security defense in edge devices, thereby advancing next-generation edge sensing and computing capabilities.

边缘设备的普遍使用，如物联网设备、智能手机、增强现实/虚拟现实头显、送货无人机和自动驾驶车辆，已经经历了明显的上升趋势。这一趋势为设备上的智能和各种边缘感知和计算应用提供了前所未有的机遇。人工智能（AI）已经成为提升这些新兴应用效率的关键推动力，包括增强现实/虚拟现实应用、智能音频助手系统和基于行为的用户身份验证等。然而，对AI的日益依赖也引入了固有的安全漏洞，在实际环境中部署这些应用时会带来重大威胁。本次演讲旨在讨论通过硬件-软件协同设计和设备上的AI实现的AI-增强边缘感知和计算的最新进展，重点突出它们对实现有效推断的重要贡献。此外，它还将深入探讨与AI整合相关的新攻击面，如对抗性攻击和后门攻击。将呈现增强现实/虚拟现实应用和智能边缘音频系统的案例研究以阐明这些概念。此外，本次演讲还将探讨新的机会，如领域不变建模，利用AI增强边缘设备的效率并加强安全防御，从而推进下一代边缘感知和计算能力。

报告人简介: Yingying (Jennifer) Chen is a Professor and Department Chair of Electrical and Computer Engineering (ECE) and Peter Cherasia Endowed Faculty Scholar at Rutgers University. She is the Associate Director of Wireless Information Network Laboratory (WINLAB). She also leads the Data Analysis and Information Security (DAISY) Lab. She is a Fellow of ACM, a Fellow of IEEE and a Fellow of National Academy of Inventors (NAI). She is also an ACM Distinguished Scientist. Her research interests include Applied Machine Learning in Mobile Computing and Sensing, Internet of Things (IoT), Security in AI/ML Systems, Smart Healthcare, and Deep Learning on Mobile Systems. She is a pioneer in RF/WiFi sensing, location systems, and mobile security. Before joining Rutgers, she was a tenured professor at Stevens Institute of Technology and had extensive industry experiences at Nokia (previously Lucent Technologies). She has published 3 books, 4 book chapters and 300+ journal articles and refereed conference papers. She is the recipient of seven Best Paper Awards in top ACM and IEEE conferences. She is the recipient of NSF CAREER Award and Google Faculty Research Award. She received New Jersey Inventors Hall of Fame Innovator Award and is also the recipient of IEEE Region 1 Technological Innovation in Academic Award. Her research has been supported by many funding agencies including NSF, NIH, ARO, DoD and AFRL and reported in numerous media outlets including MIT Technology Review, CNN, Fox News Channel, Wall Street Journal, National Public Radio and IEEE Spectrum. She has been serving/served on the editorial boards of IEEE Transactions on Mobile Computing (TMC), IEEE Transactions on Wireless Communications (TWireless), IEEE/ACM Transactions on Networking (ToN) and ACM Transactions on Privacy and Security (TOPS). For more information, please refer to her homepage at: http://www.winlab.rutgers.edu/~yychen/.

Yingying (Jennifer) Chen是美国罗格斯大学（Rutgers University）电子与计算机工程（ECE）系教授和系主任，彼得·切拉西亚（Peter Cherasia）终身教职学者。她是无线信息网络实验室（Wireless Information Network Laboratory，WINLAB）的副主任。她还领导着数据分析与信息安全实验室（Data Analysis and Information Security，DAISY Lab）。她是ACM（Association for Computing Machinery）的会士、IEEE（Institute of Electrical and Electronics Engineers）的会士以及美国发明家国家学院（National Academy of Inventors，NAI）的会士。她还是ACM杰出科学家。她的研究兴趣包括应用于移动计算和感知、物联网（IoT）、人工智能/机器学习系统安全、智能医疗和移动系统深度学习的应用机器学习。她是射频/WiFi感知、定位系统和移动安全领域的先驱。加入罗格斯大学之前，她是史蒂文斯理工学院（Stevens Institute of Technology）的终身教授，并在诺基亚（Nokia，前卢森特技术公司）拥有丰富的行业经验。她已出版3本书、4个书籍章节和300多篇期刊文章和经过同行评议的会议论文。她是多个顶级ACM和IEEE会议的七项最佳论文奖得主。她曾获得美国国家科学基金会（NSF）职业生涯奖（NSF CAREER Award）和谷歌教师研究奖（Google Faculty Research Award）。她获得了新泽西发明家名人堂创新者奖，并获得了IEEE第1区学术技术创新奖。她的研究得到了包括NSF、NIH、ARO、DoD和AFRL在内的多个资助机构的支持，并在许多媒体中报道，包括麻省理工科技评论（MIT Technology Review）、CNN、福克斯新闻频道、《华尔街日报》、国家公共广播电台（National Public Radio）和IEEE Spectrum。她曾担任/正在担任IEEE移动计算交易（IEEE Transactions on Mobile Computing，TMC）、IEEE无线通信交易（IEEE Transactions on Wireless Communications，TWireless）、IEEE/ACM网络交易（IEEE/ACM Transactions on Networking，ToN）和ACM隐私与安全交易（ACM Transactions on Privacy and Security，TOPS）的编辑委员会成员。更多信息，请参阅她的主页： http://www.winlab.rutgers.edu/~yychen/。

邀请人：蒋洪波

联系人：胡靖阳