Tutorials
Tutorial 1: Web Identity Security (WIS).
Abstract:
A web identity is an identifier that uniquely distinguishes and describes an entity (which may be a person, an organization, a device or a network resource) in cyberspace. Web identity security focuses on accurate identity verification and prevention of identity impersonation, fraud, leakage, theft, etc. Nowadays, the increasing scale of the Web gives rise to the problems of “Password Fatigue”, “Phishing Attacks” and “Brute Force Password Attacks”, and brings great challenges to the currently dominant password-based web identity authentication scheme. In this tutorial, we will first present the threats and challenges to Web security identity security and then introduce a few solutions and suggestions, in particular, a new web identity authentication scheme we proposed by introducing a module named “Trusted User Agent” in the authentication process, which is compatible with the current password-based scheme. Specifically, user account information is automatically generated and stored at the user agent, and is sent by the user agent directly to the destination server of the user-intended website being browsed on a terminal for authentication. The server then authorizes the corresponding terminal after successful authentication to complete the authentication process in the closed loop. Moreover, our new mechanism is able to protect website from phishing and malicious requests. A system based on this scheme named “denglu1” has been developed, providing users with convenience and security. In addition, we will also introduce our solutions to phishing, which is another severe threat to Web identity security. We have developed a phishing detection mechanism based on parasitic community and a safe QR code scanner to detect potential phishing URLs, which not only reaches an accuracy of 99.2%, but is the only system in the world capable of discovering phishing targets.
A web identity is an identifier that uniquely distinguishes and describes an entity (which may be a person, an organization, a device or a network resource) in cyberspace. Web identity security focuses on accurate identity verification and prevention of identity impersonation, fraud, leakage, theft, etc. Nowadays, the increasing scale of the Web gives rise to the problems of “Password Fatigue”, “Phishing Attacks” and “Brute Force Password Attacks”, and brings great challenges to the currently dominant password-based web identity authentication scheme. In this tutorial, we will first present the threats and challenges to Web security identity security and then introduce a few solutions and suggestions, in particular, a new web identity authentication scheme we proposed by introducing a module named “Trusted User Agent” in the authentication process, which is compatible with the current password-based scheme. Specifically, user account information is automatically generated and stored at the user agent, and is sent by the user agent directly to the destination server of the user-intended website being browsed on a terminal for authentication. The server then authorizes the corresponding terminal after successful authentication to complete the authentication process in the closed loop. Moreover, our new mechanism is able to protect website from phishing and malicious requests. A system based on this scheme named “denglu1” has been developed, providing users with convenience and security. In addition, we will also introduce our solutions to phishing, which is another severe threat to Web identity security. We have developed a phishing detection mechanism based on parasitic community and a safe QR code scanner to detect potential phishing URLs, which not only reaches an accuracy of 99.2%, but is the only system in the world capable of discovering phishing targets.
Prof. Liu Wenyin
WIS Lab, Guangdong University of Technology
Liu Wenyin is currently a Professor in School of Computer Science and Technology, Guangdong University of Technology, and a team leader of the Guangdong Innovative Research Team Program. He was Deputy Director of Multimedia software Engineering Research Centre at the City University of Hong Kong from 2013 to 2016, an assistant professor in the Department of Computer Science at the City University of Hong Kong between from 2002 to 2012, and a full time researcher at Microsoft Research China/Asia from 1999 to 2001. His current research interests include blockchain, anti-phishing, Web identity authentication and management. He has BEng and MEng degrees in computer science from Tsinghua University, Beijing and a doctoral degree from the Technion, Israel Institute of Technology, Haifa. In 2003, he was awarded the International Conference on Document Analysis and Recognition Outstanding Young Researcher Award by the International Association for Pattern Recognition (IAPR). In 2010, he was elected to IAPR Fellow for his contributions to graphics recognition and anti-phishing. He had been TC10 chair of IAPR for two terms 2006-2010. He had been on the IAPR Fellow Committee for three terms 2010-2016. He had been on the editorial boards of the International Journal of Document Analysis and Recognition (IJDAR) from 2006 to 2011 and the IET Computer Vision journal from 2011-2012. He is also an angel investor in the areas of cybersecurity, blockchain, Internet plus, big data, and Robots, etc.
Tutorial 2: Person Re-Identification – Challenges and Opportunities.
Abstract:
Person Re-identification (Re-ID) is a hot research topic in Computer Vision recently, which aims to match the surveillance images containing the same person. Person Re-ID can be potentially broadly used in security surveillance, customer identification, personal behavior analysis, and etc. Person Re-ID is a quite challenging task in real-world large-scale surveillance systems, because of the diversity of view-angle, brightness, resolution, background and occlusion. Recently, quickly developed deep learning techniques promote this research greatly and have produced a great achievement in some open datasets. However, how to efficiently learn in a new unlabeled testing environment with a large-scale camera network is still an open problem. In this talk, we will introduce the latest developments of the Re-ID algorithms, analyze the open problems of this field, and try to point out the possibilities to solve the challenges.
Person Re-identification (Re-ID) is a hot research topic in Computer Vision recently, which aims to match the surveillance images containing the same person. Person Re-ID can be potentially broadly used in security surveillance, customer identification, personal behavior analysis, and etc. Person Re-ID is a quite challenging task in real-world large-scale surveillance systems, because of the diversity of view-angle, brightness, resolution, background and occlusion. Recently, quickly developed deep learning techniques promote this research greatly and have produced a great achievement in some open datasets. However, how to efficiently learn in a new unlabeled testing environment with a large-scale camera network is still an open problem. In this talk, we will introduce the latest developments of the Re-ID algorithms, analyze the open problems of this field, and try to point out the possibilities to solve the challenges.
Prof. Jianming Lv
South China University of Technology
Dr. Jianming Lv is an associate professor of South China University of Technology. He is an ACM/IEEE/CCF member. He received the BS degree from Sun Yat-Sen University in 2002, and received the PhD degree from Institute of Computing Technology, Chinese Academy of Sciences in 2008. He visits City University of Hongkong in 2017 as Senior Research Associate. His research includes data mining, computer vision and distributed computing. He has published more than 30 papers at related conferences and journals, such as CVPR, ACM CIKM, ICNP, ICPP, DASFAA, IEEE Trans. Services Computing, ACM TOMCCAP, Computer Networks and PPNA.
Back to program at a glance