Recent breakthroughs in microelectronic scaling and artificial intelligence (AI) have brought about unparalleled capacity and performance benefits, leading to the creation of new devices and systems, ranging from high-performance computing to low-power edge computing. However, as computing becomes increasingly essential in safety-critical systems such as healthcare and robotics, adversarial factors like unreliable hardware and uncertain data pose a threat to the accuracy and validity of computations.
In this presentation, I will discuss our efforts to enhance robust computing against unreliable hardware and uncertain data. Firstly, I will present our research on characterizing application robustness against hardware errors using an error injection campaign. I will also introduce our methods for improving application robustness in the face of unreliable hardware. Secondly, I will discuss our research on characterizing application robustness against uncertain data using differential fuzz testing. I will also present our methods for enhancing the robustness of applications to uncertain data.
Xun Jiao is an assistant professor in the ECE department of Villanova University. He has been a visiting scientist of Meta and a visiting student researcher of NXP Semiconductors. He obtained his Ph.D. degree from UC San Diego in 2018, and obtained the joint Bachelor’s degree from the Queen Mary University of London and Beijing University of Posts and Telecommunications in 2013.
His research interests include robust and efficient computing, AI/machine learning, brain-inspired computing, and embedded systems. He received 6 paper awards/nominations in international conferences such as DATE, EMSOFT, DSD, and SELSE. He published 50+ papers in international conferences and journals. He is an associate editor of IEEE Trans on CAD, a lead guest editor of Frontiers in Neuroscience, a TPC member of DAC, ICCAD, ASP-DAC, GLSVLSI, LCTES. His research is sponsored by NSF, NIH, and L3Harris. He has delivered an invited presentation at U.S. Congressional House. He is the recipient of 2022 IEEE “Young Engineer of the Year Award” (Philadelphia Section).