|1 December 2021 (Wed)|
|17:30-20:00||Reception & Registration|
|2 December 2021 (Thu)|
|3 December 2021 (Fri)|
|14:00-15:00||Fast Abstract Discussion|
Title Resilience of AI-driven Applications
Abstract The emerging innovations in computer science and engineering are being driven by a data driven AI/ML promise to seamlessly and significantly augment human capabilities. To be successful these systems must interact with other manmade and natural systems with a focus on the flawless capabilities of dynamic decision-making algorithms. Applications, such as, autonomous vehicles, robotic management and control, and enterprise scale computing - all driven by advanced data-analytics and artificial intelligence algorithms, have spawned a level of complexity where traditional methods cannot form the backbone for resilient and safe system design. Using data on operational failures of autonomous vehicles, surgical robots, and extreme-scale computing systems as examples, this talk will discuss features of our research that leverage probabilistic graphical models (PGMs) jointly with deep learning (DNNs) for building and validating a new generation of resilient and safety-critical AI applications.
Bio Ravishankar K. Iyer is the George and Ann Fisher Distinguished Professor of Engineering at the University of Illinois at Urbana-Champaign. He holds joint appointments in the Departments of Electrical and Computer Engineering and Computer Science, in the Coordinated Science Laboratory (CSL), the National Center for Supercomputing Applications (NCSA), and the Carl R. Woese Institute for Genomic Biology. Iyer was an initial founder of the Information Trust Institute at UIUC—a campus-wide cyber-trust research center addressing security, reliability, and safety issues in critical infrastructures, including Power, Aerospace, and Financial domains funded by the State of Illinois, Boeing, HP, and the National Science Foundation (NSF) and continues to serve as the Chief Science Officer. He leads the DEPEND Group at CSL/ECE at Illinois, with a multidisciplinary focus on systems and software that combine deep measurement-driven analytics and machine learning with applications in two essential domains: i) trust (that spans resilience and the security of critical infrastructures), and ii) health and personalized medicine. The Depend Group has developed a rich AI analytics framework that has been deployed on real-world applications in collaborations with industry, health providers, and government agencies, including NSF, NIH, and DoD. He has led several large successful projects funded by the National Aeronautics and Space Administration (NASA), Defense Advanced Research Projects Agency (DARPA), National Science Foundation (NSF), and industry. Professor Iyer is a Fellow of the American Association for the Advancement of Science, the Institute of Electrical and Electronics Engineers (IEEE), and the Association for Computing Machinery (ACM). He has received several awards, including the IEEE Emanuel R. Piore Award and the 2011 Outstanding Contributions award by the Association of Computing Machinery. Professor Iyer is also the recipient of the degree of Doctor Honoris Causa from Toulouse Sabatier University in France.
Bio Yuval Yarom is a senior lecturer at the University of Adelaide. He is interested in computer security and in cryptography, with a focus on the security implications of the interface between the software and the hardware. He is the winner of the 2020 CORE Chris Wallace Award for Outstanding Research and is a 2020 Young Tall Poppy. He has co-authored over 50 peer-reviewed publications winning multiple "best paper" awards.
Title Secure Network Measurement as a Cloud Service
Abstract Network function virtualisation enables versatile network functions as cloud services. Specifically, network measurement tasks such as heavy-hitter detection and flow distribution estimation serve many core network functions for improved performance and security of enterprise networks. However, deploying network measurement services in third-party cloud providers raises privacy and security concerns. In this talk, I will present the design of our recent work named OblivSketch - a secure network measurement service built from Intel SGX. We harness the insights from confidential computing, large-scale network flow analysis, and data-oblivious primitives to build a secure and practical network measurement service. We integrate OblivSketch into the framework of SDN and demonstrate its performance via CAIDA datasets with millions of flows.
Bio Dr Xingliang Yuan is a Senior Lecturer at the Department of Software Systems and Cybersecurity in the Faculty of Information Technology, Monash University, Australia. He obtained his PhD degree from City University of Hong Kong in 2016. His research interests include data security and privacy, secure networked system, confidential computing, machine learning security and privacy. His research has been supported by Australian Research Council, CSIRO Data61, and Oceania Cyber Security Centre. In the past few years, his work has appeared in prestigious venues in computer security and networks, such as ACM CCS, NDSS, IEEE INFOCOM. He received the best paper award in the European Symposium on Research in Computer Security (ESORICS) 2021. He was the recipient of the Dean’s Award for Excellence in Research by an Early Career Researcher at Monash Faculty of IT in 2020.
We would like to congratulate authors of the accepted papers. Please see them below.
|Mehdi Karimibiuki, Andre Ivanov and Karthik Pattabiraman||Are you for Real? Authentication in Dynamic IoT Systems|
|Maxime Ayrault, Etienne Borde, Ulrich Kühne and Jean Leneutre||Moving Target Defense Strategy in Critical Embedded Systems: A Game-theoretic Approach|
|Minhao Qiu, Peter Bazan, Tobias Antesberger, Florian Bock and Reinhard German||Reliability assessment of multi-sensor perception system in automated driving functions|
|Bruno Dias, Naghmeh Ivaki and Nuno Laranjeiro||An Empirical Evaluation of the Effectiveness of Smart Contract Verification Tools|
|Tommaso Zoppi, Andrea Ceccarelli and Andrea Bondavalli||Detecting Intrusions by Voting Diverse Machine Learners: Is It Really Worth?|
|Raul Sena Ferreira, Jean Arlat, Jeremie Guiochet and Helene Waeselynck||Benchmarking Safety Monitors for Image Classifiers with Machine Learning|
|Michael Eischer and Tobias Distler||Egalitarian Byzantine Fault Tolerance|
|Christian Linder and Oliver Theel||Extending the Concept of Voting Structures to Support Path-Based Replication Strategies|
|Kaitlyn Lee, Michael Gowanlock and Bertrand Cambou||SABER-GPU: A Response-Based Cryptography Algorithm for SABER on the GPU|
|Ning Shen, Jyh-Haw Yeh, Hung-Min Sun and Chien-Ming Chen||A Practical and Secure Stateless Order Preserving Encryption for Outsourced Databases|
|Chunyan Mu||Integrating Information Flow Analysis in Unifying Theories of Programming|
|Xuanyu Duan, Mengmeng Ge, Triet Huynh Minh Le, Faheem Ullah, Shang Gao, Xuequan Lu and M. Ali Babar||Automated Security Assessment for the Internet of Things|
|Frederico Cerveira, Jomar Domingos, Raul Barbosa and Henrique Madeira||Measuring lead times for failure prediction|
|Fumio Machida and Ermeson Andrade||Availability Modeling for Drone Image Processing Systems with Adaptive Offloading|
|Stefan Klikovits and Paolo Arcaini||Handling Noise in Search-Based Scenario Generation for Autonomous Driving Systems|
|Shahid Khan and Joost-Pieter Katoen||Synergising Reliability Modelling Languages: BDMPs and Repairable DFTs|
|B Naresh Reddy||Machine Learning Techniques for the Prediction of NoC Core Mapping Performance|
|B Naresh Reddy||An Efficient Application Core Mapping Algorithm for Wireless Network-on-Chip|
|Bo-Chen Tai, Szu-Chuang Li and Yennun Huang||A VAE Conversion Method for Private Data Linkage|