June 30, 2020
15:00 – 15:15 (CEST).
Welcome / Opening session
- Opening by Vice-rector for Research, Innovation and Transfer, UPV.
- Welcome from Honorary & General Conference Chairs
- Message from PC Chairs
Video of the session
15:15 – 15:55 (CEST).
Keynote #1
Jeannette M. Wing, , Avenessians Director of the Data Science Institute and Professor of Computer Science Columbia University, New York (USA)
June 30 @ 15:15 - 15:55 (CEST)
Keynote session video
Recent years have seen an astounding growth in deployment of AI systems in critical domains such as autonomous vehicles, criminal justice, healthcare, hiring, housing, human resource management, law enforcement, and public safety, where decisions taken by AI agents directly impact human lives. Consequently, there is an increasing concern if these decisions can be trusted to be correct, reliable, fair, and safe, especially under adversarial attacks. How then can we deliver on the promise of the benefits of AI but address these scenarios that have life-critical consequences for people and society? In short, how can we achieve trustworthy AI?
Under the umbrella of trustworthy computing, there is a long-established framework employing formal methods and verification techniques for ensuring trust properties like reliability, security, and privacy of traditional software and hardware systems. Just as for trustworthy computing, formal verification could be an effective approach for building trust in AI-based systems. However, the set of properties needs to be extended beyond reliability, security, and privacy to include fairness, robustness, probabilistic accuracy under uncertainty, and other properties yet to be identified and defined. Further, there is a need for new property specifications and verification techniques to handle new kinds of artifacts, e.g., data distributions, probabilistic programs, and machine learning based models that may learn and adapt automatically over time. This talk will pose a new research agenda, from a formal methods perspective, for us to increase trust in AI systems.
Jeannette M. Wing is Avanessians Director of the Data Science Institute and Professor of Computer Science at Columbia University. From 2013 to 2017, she was a Corporate Vice President of Microsoft Research. She is Adjunct Professor of Computer Science at Carnegie Mellon where she twice served as the Head of the Computer Science Department and had been on the faculty since 1985. From 2007-2010 she was the Assistant Director of the Computer and Information Science and Engineering Directorate at the National Science Foundation. She received her S.B., S.M., and Ph.D. degrees in Computer Science, all from the Massachusetts Institute of Technology.
Professor Wing's general research interests are in the areas of trustworthy computing, specification and verification, concurrent and distributed systems, programming languages, and software engineering. Her current interests are in the foundations of security and privacy, with a new focus on trustworthy AI. She was or is on the editorial board of twelve journals, including the Journal of the ACM and Communications of the ACM.
Professor Wing is known for her work on linearizability, behavioral subtyping, attack graphs, and privacy-compliance checkers. Her 2006 seminal essay, titled "Computational Thinking" is credited with helping to establish the centrality of computer science to problem-solving in fields where previously it had not been embraced. She is currently a member of: the National Library of Medicine Blue Ribbon Panel; the Science, Engineering, and Technology Advisory Committee for the American Academy for Arts and Sciences; the Board of Trustees for the Institute of Pure and Applied Mathematics; the Advisory Board for the Association for Women in Mathematics; and the Alibaba DAMO Technical Advisory Board. She has been chair and/or a member of many other academic, government, and industry advisory boards. She received the CRA Distinguished Service Award in 2011 and the ACM Distinguished Service Award in 2014. She is a Fellow of the American Academy of Arts and Sciences, American Association for the Advancement of Science, the Association for Computing Machinery (ACM), and the Institute of Electrical and Electronic Engineers (IEEE).
16:00 – 16:45 (CEST).
Presentation of best paper candidates
Chaired by Karthik Pattabiraman, UBC
Video of the session with Q&A
List of Papers in the session and their Teasers
- KShot: Live Kernel Patching with SMM and SGXLei Zhou Southern University of Science and Technology, Fengwei Zhang (Southern University of Science and Technology), Jinghui Liao (Wayne State University), Zhenyu Ning (Southern University of Science and Technology and Wayne State University, Jidong Xiao (Boise State University), Kevin Leach (University of Michigan), Westley Weimer (University of Michigan), Guojun Wang (Guangzhou University)
- CDN Backfired: Amplification Attacks Based on HTTP Range RequestsWeizhong Li (Tsinghua University), Kaiwen Shen (Tsinghua University), Run Guo (Tsinghua University), Baojun Liu (Tsinghua University), Jia Zhang (Tsinghua University), Haixin Duan (Tsinghua University), Shuang Hao (University of Texas at Dallas), Xiarun Chen (Peking University), Yao Wang (Beijing Information Science & Technology University)
- Online Payments by Merely Broadcasting MessagesDaniel Collins (EPFL), Rachid Guerraoui (EPFL), Jovan Komatovic (EPFL), Petr Kuznetsov (Telecom ParisTech), Matteo Monti (EPFL), Matej Pavlovic (EPFL), Yvonne-Anne Pignolet (DFINITY), Dragos-Adrian Seredinschi (Interchain Foundation – Lausanne), Andrei Tonkikh (NRU HSE), Athanasios Xygkis (EPFL)
16:55 – 17:10 (CEST).
Carter Award Presentation
University of British Columbia, Canada
Bo Fang, University of British Columbia, CA
PhD Dissertation title: “Approaches for Building Error Resilient Applications”
Defense date: February 11th, 2020
Thesis Advisor:
Karthik Pattabiraman (University of British Columbia, CA)
Dissertation Summary: “Bo Fang’s thesis addresses the problem of transient hardware faults in high performance computing (HPC) systems. Starting form the idea that most transient hardware faults have no significant impact at the software layer, Bo’s thesis proposes an error propagation model and a crash model to identify which faults really matter, particularly the ones that may cause silent data corruption and crashes, in order to selectively trigger recovery actions. Subsequently, Bo proposes the innovative idea of applying the roll-forward recovery scheme in standard checkpoint/restart system to allow trading confidence in results for efficiency in both performance and energy saving. Bo’s work has already been making an impact on the design and implementation of HPC systems at two national labs in the US, namely Pacific Northwestern National Labs (PNNL), and Los Alamos National Labs (LANL). ”
.
Teaser
.
Video of the session with Q&A
17:15 – 18:30 (CEST).
Research Track #1 || Research Track #2 || Industry Track #1
Chaired by Saurabh Bagchi, Purdue Univ.
Video of the session with Q&A
List of Papers in the session and their Teasers
- Comprehensive Java Metadata Tracking for Attack Detection and RepairJeff Perkins (MIT/CSAIL), Jordan Eikenberry (MIT/CSAIL), Alessandro Coglio (Kestrel Institute), Martin Rinard (MIT/CSAIL)
- Trace Sanitizer - Eliminating the Effects of Non-determinism on Error Propagation AnalysisHabib Saissi (Technische Universität Darmstadt), Stefan Winter (Technische Universität Darmstadt), Oliver Schwahn (Technische Universität Darmstadt), Karthik Pattabiraman (University of British Columbia), Neeraj Suri (Lancaster University)
- JSKernel: Fortifying JavaScript against Web Concurrency Attacks via a Kernel-like StructureZhanhao Chen (Palo Alto Networks), Yinzhi Cao (Johns Hopkins University)
- Scarecrow: Deactivating Evasive Malware via Its Own Evasive LogicJialong Zhang (ByteDance), Zhongshu Gu (IBM Research), Jiyong Jang (IBM Research), Dhilung Kirat (IBM Research), Marc Ph. Stoecklin (IBM Research), Xiaokui Shu (IBM Research), Heqing Huang (ByteDance)
- CATI: Context-Assisted Type Inference from Stripped BinariesLigeng Chen (Nanjing University), Zhongling He (Nanjing University), Bing Mao (Nanjing University)
Chaired by Atul Prakash, Univ. of Michigan
Video of the session with Q&A
List of Papers in the session and their Teasers
- PolygraphMR: Enhancing the Reliability and Dependability of CNNsSalar Latifi (University of Michigan), Babak Zamirai (University of Michigan), Scott Mahlke (University of Michigan)
- ML-driven Malware for Targeting AV Safety Saurabh Jha (UIUC)Shengkun Cui (UIUC), Subho Banerjee (UIUC), James Cyriac (UIUC), Timothy Tsai (NVIDIA), Zbigniew Kalbarczyk (UIUC), Ravi Iyer (UIUC)
- Leaky DNN: Stealing Deep-learning Model Secret with GPU Context-switching Side-channelJunyi Wei (Fudan University), Yicheng Zhang (University of California, Irvine), Zhe Zhou (Fudan University), Zhou Li (University of California, Irvine), Mohammad Abdullah Al Faruque (University of California, Irvine)
- An Experimental Study of Reduced-Voltage Operation in Modern FPGAs for Neural Network AccelerationBehzad Salami (Barcelona Supercomputing Center (BSC)), Baturay Onural (TOBB UNIVERSITY OF ECONOMICS AND TECHNOLOGY), Ismail Emir Yuksel (TOBB UNIVERSITY OF ECONOMICS AND TECHNOLOGY), FAHRETTIN KOC (TOBB UNIVERSITY OF ECONOMICS AND TECHNOLOGY), Oguz Ergin (TOBB UNIVERSITY OF ECONOMICS AND TECHNOLOGY), Adrian Cristal (Barcelona Supercomputing Center (BSC), Osman Unsal (Barcelona Supercomputing Center (BSC)), Hamid Sarbazi-Azad (Sharif University of Technology, IPM), Onur Mutlu (ETH Zurich)
- (Practice report): Quantifying DNN Model Robustness to the Real-World Threats Zhenyu Zhong (Baidu Research Institute)Zhisheng Hu (Baidu Research Institute), Xiaowei Chen (Baidu Research Institute)
Chaired by Harigovind V. Ramasamy, Amazon
Video of the session with Q&A .List of Papers in the session and their Teasers
- Robustness Inside Out TestingDeborah Katz (School of Computer Science, Carnegie Mellon University), Milda Zizyte (Department of Electrical and Computer Engineering, Carnegie Mellon University), Casidhe Hutchison (National Robotics Engineering Center, Carnegie Mellon University), David Guttendorf (National Robotics Engineering Center, Carnegie Mellon University), Patrick Lanigan (National Robotics Engineering Center, Carnegie Mellon University), Eric Sample (National Robotics Engineering Center, Carnegie Mellon University), Philip Koopman (Department of Electrical and Computer Engineering, Carnegie Mellon University), Michael Wagner (Edge Case Research), Claire Le Goues (School of Computer Science, Carnegie Mellon University)
- Towards Host Intrusion Detection For Embedded Industrial SystemsMarine Kadar (SYSGO GmbH), Sergey Tverdyshev (SYSGO GmbH), Gerhard Fohler (TU Kaiserslautern)
- The Monitor as Key Architecture Element for Safe Self-Driving CarsAyhan Mehmed (TTTech Auto AG), Moritz Antlanger (TTTech Auto AG), Wilfried Steiner ((TTTech Computertechnik AG)