报告题目: Adversarial signal processing
报告人: Mauro Barni教授 (University of Siena 意大利锡耶纳大学)
报告时间: 9月26日上午10:00，四楼报告厅
摘要:Security-oriented applications of signal processing have received increasing attention in the last years. Digital watermarking, steganography and steganalysis, multimedia forensics, biometric signal processing, video-surveillance, are just a few examples of such an interest. In many cases, though, researchers have failed to recognize the single most unique feature behind any security-oriented application, i.e. the presence of one or more adversaries aiming at making the system fail. One of the most evident consequences is that security requirements are misunderstood, e.g. quite often security is exchanged for robustness. This has long been the case, for instance, in digital watermarking, where it took several years to recognize that robustness and security are contrasting requirements calling for the adoption of different countermeasures. In a similar way, security issues in biometric research are often neglected, privileging pattern recognition issues more related to robustness than security. Similar concerns apply to multimedia forensics, network flow analysis, spam filtering etc ... Even when the need to cope with the actions of a malevolent adversary is taken into account, the proposed solutions are often ad-hoc, failing to provide a unifying view of the challenges that such scenarios pose from a signal processing perspective. Times are ripe to go beyond this limited view and lay the basis for a general theory that takes into account the impact that the presence of an adversary has on the design of effective signal processing tools, i.e. a theory of adversarial signal processing.
It is the aim of this talk to: i) review the scattered works carried out so far in different disciplines including: watermarking security and data hiding, adversary-aware multimedia forensics, biometric spoofing, adversarial machine learning, network intrusion detection, traffic analysis, attacks against reputation systems and so on; ii) propose a unifying framework for adversarial signal processing; iii) discuss a roadmap for future research in this field.
个人简介：
Prof. Barni received the Ph.D. degree in informatics and telecommunications from the University of Florence, Italy in 1995. He is currently an Associate Professor with the University of Siena, Italy. Prof. Barni is a fellow of the IEEE. He is appointed as a Distinguished Lecturer of the IEEE Signal Processing Society from 2012 to 2013. He was a recipient of the IEEE SIGNAL PROCESSING MAGAZINE Best Column Award in 2008, and the IEEE Geoscience and Remote Sensing Society Transactions Prize Paper Award in 2011. He was the founding Editor-in-Chief of the EURASIP Journal on Information Security. He currently serves as an Associate Editor of the IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY and the IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY. From 2010 to 2011, he was the Chairman of the IEEE Information Forensic and Security Technical Committee of the Signal Processing Society. He has been a member of the IEEE Multimedia Signal Processing Technical Committee and the Conference Board of the IEEE Signal Processing Society.
During the last decade, his activity has focused on digital image processing and information security, with a particular reference to the application of image processing techniques to copyright protection (digital watermarking) and multimedia forensics. Recently, he has been studying the possibility of processing signals that have been previously encrypted without decrypting them. He led several national and international research projects on these subjects. He has authored about 270 papers, and holds four patents in the field of digital watermarking and document protection. He has coauthored the book Watermarking Systems Engineering (Dekker, 2004). His papers on digital watermarking have significantly contributed to the development of such a theory in the last decade.