Cybersecurity

Trustworthy Machine Learning Challenge 2022

The Trustworthy Machine Learning Challenge aims at a broad scope of cybersecurity professionals who are trying to break into the field and apply technical skills to solve a problem or complete a task in realistic situations. Not solely focusing on offense or defense but rather, it’s an all-encompassing approach allowing teams to compete with whatever cybersecurity strengths they bring to the competition!

Winners Announced – Cybersecurity Award

The Cybersecurity award is presented to authors whose work represents outstanding and groundbreaking research in all essential aspects of cybersecurity. The award was bestowed upon three distinguished papers focused on the following perspectives:

Best Theoretical Paper
Best Practical Paper
Best Machine Learning and Security Paper

The award carries a USD $1500 prize and comes with a statue and certificate to commemorate.

GPT conjecture: understanding the trade-offs between granularity, performance and timeliness in control-flow integrity

Performance/security trade-off is widely noticed in CFI research, however, we observe that not every CFI scheme is subject to the trade-off. Motivated by the key observation, we ask three questions: (1) Does trade-off really exist in different CFI schemes? (2) If trade-off do exist, how do previous works comply with it? (3) How can it inspire future research? Although the three questions probably cannot be directly answered, they are inspiring. We find that a deeper understanding of the nature of the trade-off will help answer the three questions. Accordingly, we proposed the GPT conjecture to pinpoint the trade-off in designing CFI schemes, which says that at most two out of three properties (fine granularity, acceptable performance, and preventive protection) could be achieved.

Full Professor in Institute of Information Engineering (IIE), Chinese Academy of Sciences (CAS). His work focuses on network and system security, parallel distributed processing. He has lead important research projects including Dawning supercomputers, National Science and Technology Major Project, National High Technology Research and Development Program of China, and strategic priority research program of CAS. He has published over one hundred peer-reviewed papers. He is the director of IIE, after serving as the deputy director of IIE, the deputy director of the High Technology Research and Development Bureau of CAS.

LIU Peng received his BS and MS degrees from the University of Science and Technology of China, and his PhD from George Mason University in 1999.  Dr. Liu is a Professor of Information Sciences and Technology, founding Director of the Center for Cyber-Security, Information Privacy, and Trust, and founding Director of the Cyber Security Lab at Penn State University.   His research interests are in all areas of computer and network security.  He has published a monograph and over 260 refereed technical papers.  His research has been sponsored by NSF, ARO, AFOSR, DARPA, DHS, DOE, AFRL, NSA, TTC, CISCO, and HP.  He has served as a program (co-)chair or general (co-)chair for over 10 international conferences (e.g., Asia CCS 2010) and workshops (e.g., MTD 2016). He chaired the Steering Committee of SECURECOMM during 2008-14. He has served on over 100 program committees and reviewed papers for numerous journals. He is an associate editor for IEEE TDSC. He is a recipient of the DOE Early Career Principle Investigator Award.  He has co-led the effort to make Penn State a NSA-certified National Center of Excellence in Information Assurance Education and Research.  He has advised or co-advised over 30 PhD dissertations to completion.