Adversarial Multimedia Forensics (eng)

This book explores various aspects of digital forensics, security and machine learning, while offering valuable insights into the ever-evolving landscape of multimedia forensics and data security. This book’s content can be summarized in two main areas. The first area of this book primarily addresses techniques and methodologies related to digital image forensics. It discusses advanced techniques for image manipulation detection, including the use of deep learning architectures to generate and manipulate synthetic satellite images. This book also explores methods for face recognition under adverse conditions and the importance of forensics in criminal investigations. Additionally, the book highlights anti-forensic measures applied to photos and videos, focusing on their effectiveness and trade-offs.

The second area of this book focuses on the broader landscape of security, including the detection of synthetic human voices, secure deep neural networks (DNNs) and federated learning in the context of machine learning security. It investigates novel methods for detecting synthetic human voices using neural vocoder artifacts, and it explores the vulnerabilities and security challenges of federated learning in the face of adversarial attacks. Furthermore, this book delves into the realms of linguistic steganography and steganalysis, discussing the evolving techniques that utilize deep learning and natural language processing to enhance payload and detection accuracy.

Overall, this book provides a comprehensive overview of the ever-evolving field of digital forensics and security, making it an invaluable resource for researchers and students interested in image forensics, machine learning security and information protection. It equips readers with the latest knowledge and tools to address the complex challenges posed by the digital landscape. Professionals working in this related field will also find this book to be a valuable resource.

Ehsan Nowroozi is a Senior Lecturer (Associate Professor) at Ravensbourne University London, Department of Business and Computing, London, UK. He received his doctorate from Siena University in 2020. He is a highly skilled researcher in the field of artificial intelligence for cybersecurity that addresses areas such as adversarial machine learning (Adv-ML), adversarial multimedia forensics (Adv-MF), network security, and digital forensics (DF). To makes AI systems more secure and resilient, Ehsan’s work emphasizes determining and defending against adversarial threats. His research has had a significant impact on the development of AI-cyber and the ability to defend against cyber threats. He had four postdocs in different high-prestige universities, including a Research Fellow at the Centre for Secure Information Technologies (CSIT) at Queen’s University Belfast in the United Kingdom, a Research Fellow at the Security and Privacy Research Group (SPRITZ) at the University of Padua in Italy, a Research Fellow at the Visual Information Processing and Protection (VIPP) at the University of Siena in Italy, a Research Fellow at the Sabanci University in Turkey. He was also an assistant professor at Bahcesehir University, Istanbul, Turkey. He has worked on a variety of projects funded by renowned institutions, such as DARPA, the Air Force Research Laboratory (AFRL) of the U.S. government, the Italian Ministry of University and Research (MUR), and THALES United Kingdom. He serves as a reviewer for prominent journals, such as IEEE TNSM, IEEE TIFS, and IEEE TNNLS. In addition, he has been a senior member of the Institute of Electrical and Electronics Engineers (IEEE) since 2022 and an ACM Professional member since 2023.

Dr.Kassem Kallas is a seasoned Research Scientist with expertise in the fields of Machine Learning (ML) and Artificial Intelligence (AI). He has a wealth of experience in applying these concepts to real-world problems. Dr. Kallas earned his Ph.D. in Information Engineering and Sciences from the University of Siena, Italy.He has worked on a variety of projects, including ones funded by renowned institutions such as DARPA, Air Force Research Laboratory (AFRL) of the U.S. government, and the Italian Ministry of University and Research (MUR) to research adversarial deep learning and adversarial signal processing. He worked on applying deep learning to wireless communication systems at the National Institute of Standards and Technology (NIST), USA.In addition to his academic and professional accomplishments, Dr. Kallas has gained valuable experience in the business and industrial sectors. He worked as an R&D scientist at ViDiTrust srl and AI consultant at Centrica-ImagineMore. Dr. Kallas is currently a research scientist at the French National Institute for Research in Digital Science and Technology (INRIA), where he continues to make significant contributions to the field. He has also been recognised for his achievements with the Best Paper Award at the Ninth International Conference on Advances in Multimedia (MMEDIA) in 2017 and top 3% paper award at ICASSP 2023. He is a Senior Member of IEEE and is part of the IEEE Young Professionals, IEEE Signal Processing Society, the European Association for Signal Processing (EURASIP), and Asia-Pacific Signal and Information Processing Association (APSIPA). In addition, he has been a reviewer at the IEEE WCNC’2016, IRACON-WS 2017, Inscrypt 2019 and iSES 2019 conferences and the IEEE Transactions on Information Forensics and Security (TIFS), IEEE Transactions on Signal Processing, EURASIP Journal on Information Security and National Institute of Standards and Technology (NIST) journal of research.He has been a technical committee - PC member at the 51st International Carnahan Conference on Security Technology ICCST 2017, and a Session Chair for NGN and Network Management at IARIA Ninth International Conferences on Advances in Multimedia (MMEDIA), 2017. He also participated in the ITU AI/ML in 5G 2020 Challenge and proposed an AI-based solution to the problem statement ”Beam-Selection in Millimeter-Wave MIMO Systems”. His research interests include Game-theoretic concepts for Adversarial Signal Processing, pattern recognition, and image processing for anti-counterfeiting applications, and Machine Learning security threats and defences. In his spare time, Dr. Kallas volunteers as a mentor at IEEE Collabortec. He is also pursuing an Executive Master of Business Administration (E-MBA) in Strategic Leadership at Valar Institute at Quantic School of Business and Technology to further enhance his expertise in the field of business.
Dr. Alireza Jolfaei is an Associate Professor in Cybersecurity and Networking in the College of Science and Engineering at Flinders University. He is a Senior Member of the IEEE and a Distinguished Speaker of the ACM on the topic of Cybersecurity. He has previously been a faculty member with Macquarie University and Federation University in Australia, and Temple University in the USA. He received a Ph.D. degree in Applied Cryptography from Griffith University, Gold Coast, Australia. His main research interest is in Cyber-Physical Systems Security, where he investigates the hidden interdependencies in industrial communication protocols and aims to provide fundamentally new methods for security-aware modelling, analysis and design of safety-critical cyber-physical systems in the presence of cyber-adversaries. He has been a chief investigator of several internal and external grants with a total amount exceeding $2,6 million. He successfully supervised eight HDR students to completion. He received the prestigious IEEE Australian Council award for his research paper published in the IEEE Transactions on Information Forensics and Security.