Keynotes of IWDCF 2017


Keynote I:

Intelligent Surveillance

Speaker: Dr. Wei Qi Yan

Auckland University of Technology, New Zealand

Abstract: Surveillance is being increasingly used for security applications such as monitoring of shopping malls and ATMs as well as industrial supervisory use. The decreasing costs coupled with rapid miniaturization of video cameras have enabled its widespread use on highways, airports, railway stations and on-board vehicles. The recent trend of coupling video cameras to cell-phones will only accelerate this trend. Therefore, research in video surveillance is moving into the mainstream with the focus on day-to-day applications and uncontrolled outdoor scenarios. And it is moving away from mere data collection with manual observation to intelligent analysis of events and actions at a semantic level without the intervention of humans. In this talk, Dr. Yan will introduce intelligent surveillance from practice to theory, and then applying the theory to practical applications, especially the applications of deep learning and AI technologies in surveillance computing at object and event levels, the talk will emphasize the computing in observation, learning, presentation and reasoning.

Dr. Wei Qi Yan received his PhD degree from Chinese Academy of Sciences, Beijing China; he is with the Auckland University of Technology (AUT) at present; his expertise is in digital security, surveillance, privacy and forensics; he is leading the Computing and Cyber Security (CCS) Research Group at AUT. Dr. Yan is the editor-in-chief (EiC) of the International Journal of Digital Crime and Forensics (IJDCF); he was an exchange computer scientist between the Royal Society of New Zealand (RSNZ) and the Chinese Academy of Sciences (CAS), China; he is a member of the ACM, a senior member of the IEEE, TC members of the IEEE. Dr. Yan is a guest (adjunct) professor with PhD supervision of the State Key Laboratory of Information Security (SKLOIS), Chinese Academy of Sciences, China.






Keynote II:

I didnt download the pornography video and I dont know how it got into my computer C Can we trust the suspect?

Speaker: Dr. Kam Pui Chow

Center for Information Security and Cryptography, University of Hong Kong, Hongkong, China

Abstract: In the past few years, existing of digital evidence inside the suspects computer may not be sufficient for conviction. Due to the advance in malware and virus, the defendant may hire his own expert to argue that the digital evidence, e.g. child pornography, was inserted into his computer by malware or virus without the knowledge of the user. In this talk, the speaker will discuss how to apply probabilistic model to estimate the chance that the digital evidence appears inside the suspects computer without the users knowledge.

Dr. K. P. Chow is the Associate Professor of Department of Computer Science and the Associate Director of the Center for Information Security and Cryptography at The University of Hong Kong. Dr. Chows areas of research interest are computer forensics, cryptography, computer security, Internet surveillance and privacy. Dr. Chow has been working on the Internet piracy monitoring system Lineaments, which were adopted by HKSAR Customs and Excise Department. He has also published research papers on computer forensics, data security and cryptography in local and international conferences and journals.  Dr. Chow has served as a member of the Program Committee of the international computer forensic workshop SADFE (Systematic Approaches to Digital Forensic Engineering) and was the conference chairman of the Sixth IFIP WG 11.9 International Conference on Digital Forensics held in 2010 in Hong Kong.  From 2010-2013, and from 2016, Dr. Chow is the Chairman of the Information Security and Forensics Society (ISFS), a professional body for digital forensics experts in Hong Kong.  In the past few years, Dr. Chow has been invited to be a computer forensic expert to assist the Court in Hong Kong.




Keynote III:

JPEG Image Forensics

Speaker: Dr. Bin Li

Shenzhen Key Laboratory of Media Security, Shenzhen University, China

Abstract: Knowledge about the JPEG compression history of images is of important interest to forensic experts, whose aim is to trace the processing history and detect possible forgeries. This talk will give a brief review on reported works on identifying whether an image is uncompressed or has been compressed previously, whether an image has been compressed once or twice, and on estimating the JPEG quantization steps (or quantization table). Our proposed solutions based on extracting features respectively from coefficients, from noise statistics, and from CNN (convolutional neural network) will be given.

Dr. Bin Li received the B.E. degree in Communication Engineering and the Ph.D. degree in Communication and Information System from Sun Yat-Sen University, Guangzhou, China, in 2004 and 2009, respectively. He was a Visiting Scholar with the New Jersey Institute of Technology, Newark, NJ, USA. He is currently a Research Fellow and an Associate Professor with Shenzhen University, Shenzhen, China, where he joined in 2009. He is a member of the Shenzhen Key Laboratory of Media Security. His current research interests include multimedia forensics, image processing, and pattern recognition. Dr. Li was a recipient of Shenzhen Talent (High-level Professionals) and CSC (China Scholarship Council) Scholarship. He has published more than 40 IEEE journal and conference proceeding papers, mainly focus on information hiding, media forensics, and steganalysis. He is the Principal Investigator of several research grants, including grants supported by National Natural Science Foundation of China. Dr. Li is the journal editor of KSII Transactions on Internet and Information Systems and the IEEE chapter secretary for IEEE Shenzhen Coms/SPS Chapter. He is the committee member of Image Forensics and Security Committee for China Society of Image and Graphics.




Keynote IV:

Digital Image/Video Forensics: A Model-based Computer Vision Approach

Speaker: Dr. Wei Wang

Institute of Automation, Chinese Academy of Sciences, China

Abstract: A plenty of viciously doctored digital images are produced everyday with several easy-to-use editing softwares like PhotoShop. And, the development of Computer Graphics (CG) technology has made it more difficult to distinguish virtual media from reality. A rich toolset of forensic methods is urgently needed. Being an abundant source for forensic clues, the imaging environment is still not well-investigated. In this talk, I will firstly revisit some forensic clues about imaging environment during image generation process, and then introduce our contributions on how to estimate and harness them for forensics. The explored clues include complex lighting environment, scene and camera geometry and physiological signal of human. Behind these forensic methods is a paradigm of model-based computer vision for the estimation of environment information. Some related techniques are 3D morphable model, camera projection model and light reflection model.

Dr. Wei Wang received his BSc degree in Computer Science and Technology from North China Electric Power University, in 2007, and his PhD degrees in Pattern Recognition from the Institute of Automation, Chinese Academy of Sciences (CASIA) in 2012. He is currently an assistant professor of the National Laboratory of Pattern Recognition (NLPR), CASIA. He is a member of IEEE, CCF, CAAI, etc. He is also a member of technical committee (TC) on Computer Vision of CCF, TC on Digital Forensics and Security of CSIG, TC on Pattern Recognition of CAAI, etc. His current research interests include artificial intelligence and its security problem, image and video forensics and steganalysis, and information content security. Dr. Wang has published more than 30 research papers on these topics in refereed international journals and conferences including TIFS, WIFS, ICME, etc.