Prof. Fenghua Li,
Institute of Information Engineering
Jul. 24, Saturday, 14:00-14:40 PM, Kendo chamber
Title: Privacy Computing and its Research Scope
Abstract: With the rapid development of information technology and the continuous evolution of service mode, it leads to a common situation in which a massive amount of users’personal information interacts across information systems, digital ecosystems, and even national network boundaries. However, existing privacy-preserving schemes cannot provide systematic privacy preservation, and problems like dynamic privacy measurement and extended control, tracing the source of privacy violations are still unsolved, therefore, it is necessary to set up a completely theoretical system of privacy preservation. This report includes: definition of privacy computing, key technical links and the computing framework of privacy computing, some important characteristic, intelligent sensing and dynamical measurement of private information, algorithm design criteria, evaluation of the privacy-preserving effect, privacy computing language, determining and tracing the privacy violations, and system architecture of privacy Information. Finally, we discuss the prospect of future research trends.
Biography: Dr. Fenghua Li is working as a professor in Institute of Information Engineering (IIE), Chinese Academy of Sciences, and doctoral supervisors in multiple majors including Cyber Security, Cryptography, Computer Systems Architecture and Information Security, in IIE, Xidian University, and University of Science and Technology of China. His current research interests include network security, system security, privacy computing and trusted computing. He has published more than 150 papers in many international journals and conferences such as IEEE TMC, TIFS, IoT-J, INFOCOM, and held more than 30 national invention patents. He has also received the best paper award of IEEE TRUSTCOM 2015.
Prof. Zheng Qin,
Hunan University
Jul. 24, Saturday, 14:40-15:20 PM, Kendo chamber
Title: Artificial Intelligence and Security: Challenges, Methodologies and Future Directions
Abstract: Artificial Intelligence (AI) technologies have been developed for numerous systems and services, such as face recognition, smart health, auto-drive, smart city, etc. According to the laws and regulations in China, it is desirable to develop both security techniques for AI applications and AI-driven security techniques. On the one hand, we introduce security techniques to protect the privacy of participants when utilizing AI to make timely and safe decisions in unpredictable environments. On the other hand, we illustrate several AI-driven techniques to enhance system security. Finally, we discuss future directions of AI and Security.
Biography: Zheng Qin received his Ph.D. degree in computer science from Chongqing University, China, in 2001. He was a visiting scholar at Michigan State University from 2010 to 2011. He is a full professor and vice dean in the College of Computer Science and Electronic Engineering, Hunan University, China. He is the director of the Hunan Key Laboratory of Big Data Research and Application, and the vice director of the Hunan Engineering Laboratory of Authentication and Data Security, Changsha, China. His research interests include information and AI security，data science and technology, etc.
Prof. Xinyi Huang,
Fujian Normal University
Jul. 24, Saturday, 15:20-16:00 PM, Kendo chamber
Title: Towards Efficient Privacy-Preserving Inspection of TLS Encrypted Traffic
Abstract: Network middleboxes perform deep packet inspection to detect anomalies and suspicious activities in network traffic. However, increasingly these traffic are encrypted and middleboxes can no longer make sense of them. This raises the problem of privacy-preserving inspection on TLS encrypted traffic. In this talk will first introduce the need for TLS traffic inspection and the problem with the existing approach. Three recent proposals, namely Blindbox, PrivDPI and Pine, will be then introduced. Finally, I will present conclusion and future direction.
Biography: Xinyi Huang received his Ph.D. degree from the School of Computer Science and Software Engineering, University of Wollongong, Australia, in 2009. He is currently a Professor at the College of Mathematics and Informatics, Fujian Normal University, China. His research focuses on cryptography and its applications. He has published over 160 research papers in refereed international conferences and journals, such as ACM CCS, Asiacrypt, Crypto, IEEE TIFS and IEEE TDSC. He is in the Editorial Board of International Journal of Information Security and SCIENCE CHINA Information Sciences. He has served as the program/general chair or program committee member in over 120 international conferences.
Prof. Jin Li,
Guangzhou University
Jul. 24, Saturday, 16:20-17:00 PM, Kendo chamber
Title: How to Ensure Secure Data Sharing with Blockchain in IoT
Abstract: With the rapid development of IoT techniques, IoT networks constantly generate a large amount of data which contain valuable information for various industrial applications after collecting and analyzing. However, it is almost impossible to enable users to effectively contribute their data without privacy guarantees and incentive mechanisms. Such challenges seriously restrict the data sharing in IoT networks. To this end, based on the blockchain platform, we propose a data incentive mechanism to provide data privacy and fairness measures for users in IoT. Moreover, we give two different constructions of the proposed mechanism and analyze their performances on privacy protection and transaction efficiency.
Biography: Jin Li is currently a professor and vice dean of School of Computer Science, Guangzhou University. He got his Ph.D degree in information security from Sun Yat-sen University at 2007. His research interests include design of secure protocols in Artificial Intelligence, Cloud Computing (secure cloud storage and outsourcing computation) and cryptographic protocols. He has published more than 100 papers in international conferences and journals, including IEEE INFOCOM, IEEE TIFS, IEEE TPDS, IEEE TOC and ESORICS etc. His work has been cited more than 11000 times at Google Scholar and the H-Index is 40. He is Editor-in-Chief of International Journal of Intelligent Systems. He also serves as Associate editor for several international journals, including IEEE Transactions on Dependable and Secure Computing, Information Sciences.
Prof. Chao Shen,
Xi’an Jiaotong University
Jul. 24, Saturday, 17:00-17:40 PM, Kendo chamber
Title: Data-Driven Security Analysis of Machine Learning Systems
Abstract: Human society is witnessing a wave of machine learning (ML) driven by deep learning techniques, bringing a technological revolution for human production and life. In some specific fields, ML has achieved or even surpassed human-level performance. However, most previous machine learning theories have not considered the open and even adversarial environments, and the security and privacy issues are gradually rising. Besides of insecure code implementations, biased models, adversarial examples, sensor spoofing can also lead to security risks, which are hard to be discovered by traditional security analysis tools. This talk reviews previous works on ML system security and privacy, revealing potential security and privacy risks. Firstly, we introduce a threat model of ML systems, including attack surfaces, attack capabilities and attack goals. Second, we analyze security risks and countermeasures in terms of four critical components in ML systems: data input (sensor), data preprocessing, machine learning model and output. Finally, we discuss future research trends on the security of ML systems. The aim is to arise the attention of the computer security society and the ML society on security and privacy of ML systems, and so that they can work together to unlock ML’s potential to build a bright future.
Biography: Chao Shen is a Professor in School of Electronic and Information Engineering, and serves as the Associate Dean of School of Cyber Science and Engineering, at Xi’an Jiaotong University. He is also a member of Ministry of Education Key Lab for Intelligent Networks and Network Security. He was a research scholar in Computer Science Department of Carnegie Mellon University from 2011 to 2013. He has published over 70 papers in prestigious journals and conferences of cyber security and artificial intelligence fields such as USENIX Security, ACM CCS, IEEE TDSC, IEEE TIFS, Automatica, IEEE TNNLS, and ACM TKDD. He was the recipient of NSFC Excellent Young Scientists Fund, the recipient of the MIT TR35 China, and the young Fellow of Alibaba Damo-Academy. He serves as an associate editor of several international journals (i.e., IEEE TDSC), as well as organization committee member or program committee member of several academic conferences (i.e., ACM CCS, NDSS).