WIFS 2015, along the tradition of previous WIFS editions, will host four high quality tutorials on hot topics for the information forensics and security community, scheduled in parallel sessions during two time slots for the first day of the conference, Monday November 16, 2015. The aim of the given tutorials is to provide an overview of the state-of-the-art in specific fields. Supporting material for the tutorial will be provided to the attendees.
Privacy-Aware Data Analytics (Morning Session)
The tutorial on “Privacy-Aware Data Analytics” will be given by Shantanu Rane (Palo Alto Research Center, US).
Adversarial Signal Processing (Morning Session)
The tutorial on “Adversarial Signal Processing” will be given by Mauro Barni (University of Siena, Italy) and Fernando Pérez-González (University of Vigo, Spain).
Privacy in Smart Metering Systems (Afternoon Session)
The tutorial on “Privacy in Smart Metering Systems” will be given by Mustafa A. Mustafa (KU Leuven, Belgium), in place of Deniz Gunduz (Imperial College London, London, United Kingdom), and Georgios Kalogridis (Toshiba Telecommunications Research Laboratory in Bristol, UK).
The Open Set Recognition Problem in Information Forensics and Security (Afternoon Session)
The tutorial on “The Open Set Recognition Problem in Information Forensics and Security” will be given by Walter J. Scheirer (University of Notre Dame, US) and Anderson Rocha (University of Campinas, Brazil).
More information on each tutorial is given hereafter
Lecturer: Shantanu Rane (Palo Alto Research Center, US)
Big data analytics presents exciting opportunities for individuals, corporations and governments. Applications include discovering elusive treatments and cures, streamlining our transportation systems, securing people and infrastructure against terrorism, distributing and pricing energy in smart grids, driving customer-centric businesses on the internet, and many more. However, the big data requirement appears, almost fundamentally, to conflict with the idea of privacy. Indeed, much of big data analytics today involves indiscriminate information gathering with scant regard for individual privacy. How can expressive analysis be conducted while protecting the privacy of people whose data is collected?
Our objective is to present a systematic overview of privacy-preserving analytics, that exposes the various capabilities, limitations and tradeoffs. We will motivate the need for privacy-aware analytics, by specifying the requirements of stakeholders in the big data analytics setting. Next, we will introduce privacy technologies that have been used to address this problem, including cryptographic techniques (e.g., homomorphic encryption, garbled circuits, searchable encryption, verifiable computing and more), and statistical mechanisms (k-anonymity and its variants, differential privacy). We will highlight the gaps between what can be achieved by existing techniques and what is needed for privacy-aware analytics. In these gaps reside several new challenges for the research community.
Shantanu Rane is a Senior Member of the Research Staff at Palo Alto Research Center (PARC). His research interests are in applied cryptography, signal processing and information theory. He has previously worked at Mitsubishi Electric Research Laboratories (MERL).Shantanu participated in the ITU-T/MPEG H.264/AVC standardization activity, and was an editor and member of the US delegation in the ISO/IEC JTC1 SC37 Subcommittee on Biometrics. He is an associate editor for the IEEE Transactions on Information Forensics and Security and the IEEE Signal Processing Magazine. Shantanu has a Ph.D. in electrical engineering from Stanford University.
Lecturers: Mauro Barni (University of Siena, Italy) and Fernando Pérez-González (University of Vigo, Spain)
Due to rising concerns about security and privacy, and the popularity of cloud-centric services, it has only been recently that the signal processing community has started rethinking designs to account for the presence of a (malicious) adversary.The aim of this tutorial is to present the basic theory of adversarial signal processing, with numerous motivating examples taken from the fields of watermarking, multimedia forensics, traffic analysis, intrusion detection, biometrics, fingerprinting and traitor tracing, reputation systems, cognitive radio, etc. We will focus on adversarial hypothesis testing, which is arguably the best understood topic, and for which the new framework has already produced improved countermeasures. As a fundamental approach we will show how to use game theory to model the available strategies to both defender and adversary. In some cases of interest, it is possible to find an equilibrium of the game which gives the optimum strategies for both parties and the performance that each can achieve.
- Introduction and motivation
- Adversarial hypothesis testing
- Game-theoretic approach
- The source identification game
- Detecting the presence of the adversary
- Sensitivity, hill climbing and ACRE attacks
- Towards smart detectors
- Challenges and open problems
Mauro Barni graduated in electronic engineering at the University of Florence in 1991. He received the PhD in Informatics and Telecommunications in October 1995. He has carried out his research activity for almost 20 years first at the Department of Electronics and Telecommunication of the University of Florence, then at the Department of Information Engineering and Mathematics of the University of Siena. His research activity focuses on multimedia and information security, with particular reference to copyright protection, multimedia forensics and signal processing in the encrypted domain. He is co-author of almost 300 papers published in international journals and conference proceedings, he holds three patents in the field of digital watermarking and one patent dealing with anticounterfeiting technology. He is co-author of the book "Watermarking Systems Engineering: Enabling Digital Assets Security and other Applications", published by Dekker Inc. in February 2004. He is editor of the book "Document and Image Compression" published by CRC-Press in 2006. He has been the chairman of the IEEE Multimedia Signal Processing Workshop held in Siena in 2004. He was technical program co-chair of ICASSP 2014. In 2008, he was the recipient of the IEEE Signal Processing Magazine best column award. In 2010 he was awarded the IEEE Transactions on Geoscience and remote sensing best paper award. He was the founding editor in chief of the EURASIP Journal on Information Security. He has been part of the editorial board of several journals. From 2010 to 2011, he has been the chairman of the IEEE Information Forensic and Security Technical Committee of the IEEE Signal Processing Society. He has been a member of the IEEE Multimedia Signal Processing technical committee and of the conference board of the IEEE Signal Processing Society. He was appointed distinguished lecturer by the IEEE Signal Processing Society for the years 2013-2014. He is the Editor in Chief of the IEEE Transactions on Information Forensics and Security. Mauro Barni is a fellow member of the IEEE and senior member of EURASIP.
Fernando Pérez-González received the Ph.D. in Telecommunications Engineering in 1993. He is currently Full Professor at the University of Vigo, Spain, and Research Professor at the University of New Mexico. His research interests lie in the crossroads of signal processing, security/privacy and communications, in particular, those problems in which an adversary is present. Fernando has coauthored more than 200 journal and conference papers, 15 patents, and has participated in 5 European projects related to multimedia security. He has served in the Editorial Board of several international journals, including IEEE Trans. on Information Forensics and Security. He has been in the program committee of more than 100 conferences and workshops.
Privacy in Smart Metering Systems
Lecturers: Mustafa A. Mustafa (KU Leuven, Belgium), in place of Deniz Gunduz (Imperial College London, London, United Kingdom), and Georgios Kalogridis (Toshiba Telecommunications Research Laboratory in Bristol, UK)
For efficient and reliable electrical energy generation, distribution and demand side management, advanced control mechanisms have been introduced into the Smart Grid (SG). Smart electricity meters (SMs) are an essential component of the SG; they establish a two-way communication infrastructure and enable demand side management by responding to real-time pricing. However, SM readings can also reveal users' habits and behaviours as every electric appliance has its own detectable power consumption signature. Non-intrusive load monitoring techniques can be used for surveillance of users' activities in real-time. Hence, there is a significant tension between sharing data to empower SG mechanisms, and consumer privacy. Further, SM communications are vulnerable to security attacks spoofing or manipulating data and control messages, the orchestration of which at a large scale, may stress or crash the entire power network.
This tutorial will provide a comprehensive overview of growing privacy threats to SMs and the smart grid in general. Potential attacks and their impact on the grid, and various privacy preservation solutions will be reviewed. We will provide both an academic and an industry perspective on the future of SMs, and the tools that can be employed to guarantee advanced SM functionality without threatening user privacy.
Mustafa A. Mustafa received the B.Sc. degree in communications from Technical University of Varna, Varna, Bulgaria in 2007, the M.Sc. degree in Communications and Signal Processing from Newcastle University, Newcastle upon Tyne, U.K., in 2010, and the Ph.D. degree in Computer Science from the University of Manchester, Manchester, U.K., in 2015. He is a Post-doctoral Researcher at COSIC research group at KU Leuven, Belgium. His research interests include information security, data privacy, smart grid, e-health and IoT.
Deniz Gunduz received M.S. and Ph.D. degrees from NYU Polytechnic School of Engineering in 2004 and 2007, respectively. He held various positions at Princeton University, Stanford University, and CTTC (Spain). Currently, he is a Lecturer at Imperial College London. He is an Editor of the IEEE Transactions on Communications, and IEEE Journal on Selected Areas in Communications Series on Green Communications and Networking. He is the recipient of the 2014 IEEE Communications Society Best Young Researcher Award for the Europe, Middle East, and Africa Region, and the Best Student Paper Award at the 2007 IEEE International Symposium on Information Theory (ISIT).
Georgios Kalogridis received the Dipl. El. Comp. Eng. from the University of Patras, Greece, in 2000, the M.Sc. degree in Advanced Computing from the University of Bristol, U.K., in 2001, and the Ph.D. degree in Mathematics from Royal Holloway, University of London, U.K., in 2011. He is a Principal Research Engineer and a Team Leader at Toshiba Telecommunications Research Laboratory, where he has been working since 2001. His research has spanned the areas of information security, data privacy, machine learning, wireless networking and smart grid communications. In these areas, he has authored papers, invented patents, developed corporate technology prototypes, and contributed to collaborative research projects and standards.
The Open Set Recognition Problem in Information Forensics and Security
Lecturers: Walter J. Scheirer (University of Notre Dame, US) and Anderson Rocha (University of Campinas, Brazil)
Coinciding with the rise of large-scale statistical learning within the information forensics and security community there has been a dramatic improvement in automated methods for digital image forensics, forensic linguistics, network intrusion detection, and human biometrics, among many other applications. Despite this progress, a tremendous gap exists between the performance of automated methods in the laboratory and the performance of those same methods in the field. A major contributing factor to this is the way in which machine learning algorithms are typically evaluated: without the expectation that a class unknown to the algorithm at training time will be experienced during operational deployment.
The purpose of this tutorial is to introduce the WIFS audience to the open set recognition problem. A number of different topics will be explored, including supervised machine learning, probabilistic models, kernel machines, the statistical extreme value theory, and original case studies related to the topics of interest at WIFS. The tutorial is composed of three parts, each lasting approximately one hour:
- An introduction to the open set recognition problem?
- Algorithms that minimize the risk of the unknown
- Case studies related to images, text and network traffic
Additional information, including presentation slides and source codes, can be retrieved at http://www.ic.unicamp.br/~rocha/pub/2015-wifs/.
Walter J. Scheirer, Ph.D. is an Assistant Professor in the Department of Computer Science and Engineering at the University of Notre Dame. Prior to Notre Dame, he was a Postdoctoral Fellow in the Center for Brain Science at Harvard University. He received his Ph.D. from the University of Colorado and his M.S. and B.A. degrees from Lehigh University. Dr. Scheirer has extensive experience in the areas of security, computer vision and human biometrics, with an emphasis on advanced learning techniques. His overarching research interest is the fundamental problem of recognition, including the representations and algorithms supporting solutions to it.
Anderson Rocha received his B.Sc degree from Federal University of Lavras, Brazil in 2003. He received his M.S. and Ph.D. from University of Campinas, Brazil in 2006 and 2009, respectively. Currently, he is an Associate Professor in the Institute of Computing, Unicamp, Brazil. His main interests include digital image and video forensics, pattern analysis, machine learning, and reasoning for complex data. He is an elected member of the IEEE IFS-TC and was co-general chair of WIFS 2011. In 2011, he was named a Microsoft Research Faculty Fellow. Finally, he is an associate editor for IEEE T-IFS.