Fall 2022
Computer Science Seminar Series
September 29, 2022
Abstract: Recent advances in AI, machine learning, and robotics have significantly enhanced the capabilities of machines. Machine intelligence is now able to support human decision-making, augment human capabilities, and, in some cases, take over control from humans and act fully autonomously. Machines are becoming more tightly embedded into systems alongside humans, interacting and influencing each other in a number of ways. Such human-AI partnerships are a new form of sociotechnical system in which the potential synergies between humans and machines are much more fully utilized. Designing, building, and deploying human-AI partnerships present a number of new challenges as we begin to understand their impact on our physical and mental well-being, our personal freedoms, and those on the wider society. In this talk, Sarvapali “Gopal” Ramchurn will focus on the challenges in designing trustworthy human-AI partnerships. He will detail the multiple elements of trust in human-AI partnerships and discuss associated research challenges. He will also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. He will conclude by giving a brief overview of the UK Research and Innovation Trustworthy Autonomous Systems Programme, a £33 million program launched in 2020 involving over 20 universities, 100+ industry partners, and over 200 researchers.
Speaker Biography: Sarvapali “Gopal” Ramchurn is a professor of artificial intelligence, a Turing Fellow, and a fellow of the Institution of Engineering and Technology. He is the director of the UK Research and Innovation Trustworthy Autonomous Systems Hub and co-director of the Shell-Southampton Centre for Maritime Futures. He is also a co-CEO of Empati, an AI startup working on decentralized green hydrogen technologies. Ramchurn’s research is mainly about the design of responsible AI for sociotechnical applications, including energy systems and disaster management. He has won multiple Best Paper Awards for his research in multi-agent systems, energy management, and disaster response, and is a winner of the 2018 AXA Research Fund Award for his work on responsible AI.
Institute for Assured Autonomy & Computer Science Seminar Series
October 18, 2022
Abstract: The introduction of machine learning and artificial intelligence creates unprecedented opportunities for achieving full autonomy. However, learning-based methods in building autonomous systems can be extremely brittle in practice and are not designed to be verifiable. In this talk, Chuchu Fan will present several of her recent efforts that combine ML with formal methods and control theory to enable the design of provably dependable and safe autonomous systems. She will introduce techniques to generate safety certificates and certified decision and control for complex autonomous systems, even when the systems have many agents, follow nonlinear and nonholonomic dynamics, and need to satisfy high-level specifications.
Speaker Biography: Chuchu Fan is an assistant professor in the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology. Before that, she was a postdoctoral researcher at the California Institute of Technology. Fan received her PhD in 2019 from the Department of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign. She earned her bachelor’s degree from Tsinghua University’s Department of Automation. Fan’s group at MIT works on using rigorous mathematics—including formal methods, machine learning, and control theory—for the design, analysis, and verification of safe autonomous systems. Her dissertation, “Formal Methods forSafe Autonomy,” won the ACM Doctoral Dissertation Award in 2020.
Institute for Assured Autonomy & Computer Science Seminar Series
November 15, 2022
Abstract: Recent years have witnessed a global phenomenon in the real-world development, testing, deployment, and commercialization of AI-enabled cyber-physical systems (CPSs) such as autonomous driving cars, drones, and industrial and home robots. These systems are rapidly revolutionizing a wide range of industries today—from transportation, retail, and logistics (e.g., robo-taxis, autonomous trucks, delivery drones/robots) to domotics, manufacturing, construction, and health care. In such systems, the AI stacks are in charge of safety- and mission-critical decision-making processes such as obstacle avoidance and lane-keeping, which makes their security more critical than ever. Meanwhile, since these AI algorithms are only components of the entire CPS enclosing them, their security issues are only meaningful when studied with direct integration of the semantic CPS problem context, which forms what we call the “semantic AI security” problem space and introduces various new AI security research challenges. In this talk, Alfred Chen will focus on his recent efforts on semantic AI security in one of the most safety-critical and fastest-growing AI-enabled CPS today, autonomous driving (AD) systems. Specifically, his group performed the first security analysis on a wide range of critical AI components in industry-grade AD systems such as 3D perception, sensor fusion, lane detection, localization, prediction, and planning. In this talk he will describe key findings and also how to address corresponding semantic AI security research challenges. Chen will conclude with a recent systemization of knowledge he performed for this growing research space, with a specific emphasis on the most critical scientific gap observed and a proposed solution.
Speaker Biography: Alfred Chen is an assistant professor of computer science at the University of California, Irvine (UCI). His research interests span AI security, systems security, and network security. His most recent research focuses on AI security in autonomous driving and intelligent transportation. His work has high impact in both academia and industry, with more than 30 research papers in top-tier venues across security, mobile systems, transportation, software engineering, and machine learning; a nationwide U.S. Department of Homeland Security United States Computer Emergency Readiness Team alert with multiple Common Vulnerabilities and Exposures Identifiers; more than 50 news pieces by major media such as Forbes, Fortune, and the BBC; and vulnerability report acknowledgments from the U.S. Department of Transportation, Apple, Microsoft, and more. Recently, Chen’s research triggered more than 30 autonomous driving companies and the V2X standardization workgroup to start security vulnerability investigations, some of which confirmed to work on fixes. Chen co-founded the International Workshop on Automotive and Autonomous Vehicle Security (co-located with the Network and Distributed System Security Symposium) and co-created DEF CON’s first AutoDriving-themed hacking competition. He has received various awards such as an NSF CAREER Award, the ProQuest Distinguished Dissertation Award, and the UCI Chancellor’s Award for Excellence in Undergraduate Research Mentorship. Chen received his PhD from the University of Michigan in 2018.
Computer Science Seminar Series
November 17, 2022
Abstract: We propose a method to introduce uncertainty to the surface reconstruction problem. Specifically, we introduce a statistical extension of the classic Poisson Surface Reconstruction algorithm for recovering shapes from 3D point clouds. Instead of outputting an implicit function, we represent the reconstructed shape as a modified Gaussian process, which allows us to conduct statistical queries (e.g., the likelihood of a point in space being on the surface or inside a solid). We show that this perspective improves PSR’s integration into the online scanning process, broadens its application realm, and opens the door to other lines of research, such as applying task-specific priors.
Speaker Biography: Silvia Sellán is a fourth-year computer science PhD student at the University of Toronto. She is advised by Alec Jacobson and working in computer graphics and geometry processing. She is a Vanier Doctoral Scholar, an Adobe Research Fellow, and the winner of the 2021 University of Toronto Arts & Science Dean’s Doctoral Excellence Scholarship. Sellán has interned twice at Adobe Research and twice at the Fields Institute of Mathematics. She is also a founder and organizer of the Toronto Geometry Colloquium and a member of the ACM Community Group for Women in Computer Graphics. Sellán is currently looking to survey potential future postdoctoral and faculty positions starting in the fall of 2024.