Special Session #1: Recent Advances in Detecting Manipulation Attacks on Biometric Systems (ADMA-2025)
Manipulated attacks in biometrics via modified images/videos and other material-based techniques, such as presentation attacks and deep fakes, have become a tremendous threat to the security world owing to increasingly realistic spoofing methods. Hence, such manipulations have triggered the need for research attention towards robust and reliable methods for detecting biometric manipulation attacks. The recent inclusion of manipulation/generation methods such as auto-encoder and generative adversarial network approaches, combined with accurate localisation and perceptual learning objectives, added an extra challenge to such manipulation detection tasks. Due to this, the performance of existing state-of-the-art manipulation detection methods significantly degrades in unknown scenarios. Apart from this, real-time processing, manipulation on low-quality medium, limited availability of data, and inclusion of these manipulation detection techniques for forensic investigation are yet to be widely explored. Hence, this special session aims to profile recent developments and push the border of the digital manipulation detection technique on biometric systems.
Organizers:
- Asst. Prof. Dr. Abhijit Das, BITS Pilani, Hyderabad, India
- Prof. Dr. Raghavendra Ramachandra, NTNU, Norway
- Dr. Naser Damer, Fraunhofer IGD, Germany
- Prof. Dr. Vitomir Štruc, University of Ljubljana, Slovenia
- Marija Ivanovska, University of Ljubljana, Slovenia
- Antitza Dantcheva, INRIA, France
Website: https://sites.google.com/view/ijcb-ss-adma-2025/home
Special Session #2: Privacy-Preserving Biometrics: Advances in Methodologies and Applications
Biometrics has become a fundamental technology for identity authentication, security, medical diagnosis, real-world human-computer interaction, etc. However, the widespread use of biometric systems raises growing concerns about privacy, security, and potential misuse of sensitive data. Therefore, developing privacy-preserving biometrics technologies is critical to ensuring both security and ethical use in real-world applications. In other words, privacy-preserving biometrics has become an essential research area due to increasing concerns over data security, identity protection, authentication, and de-identification in biometric systems. This special session aims to explore the state-of-the-art methodologies and real-world applications that enhance biometrics, while safeguarding personal privacy. The session welcomes innovative research on techniques and novel applications that contribute to the development of privacy-aware biometric systems. We seek to explore the latest technologies, discuss challenges and limitations, and propose innovative solutions to overcome the challenges for the above topics. By highlighting the latest advanced research, we aim to promote the development of Privacy-Preserving Biometrics.
Organizers:
- Dr. Jianhang Zhou, Shanghai University
- Prof. Shuping Zhao, Guangdong University of Technology
- Prof. Bob Zhang, University of Macau
- Dr. Qi Zhang, City University of Macau
- Prof. Xing Wu, Shanghai University
Website: https://sites.google.com/view/pbr-ijcb25/home
Special Session #3: Decentralised Identity and Biometric Authentication in Smart City Applications
The evolution of smart cities is redefining urban infrastructure through the integration of intelligent systems in transportation, governance, healthcare, financial services, and public safety. At the core of these services lies biometric-based authentication and access control, enabling seamless, secure interactions between citizens and digital systems. However, current implementations primarily rely on centralised architectures, which aggregate and process biometric and identity data through centrally managed machine learning models. While centralisation simplifies system management, it introduces a range of critical security, privacy, and interoperability concerns. The reliance on centralised biometric repositories creates significant vulnerabilities, as evidenced by the exposure of over 1.1 billion biometric records in 2022 across multiple sectors. According to IBM’s 2023 Cost of a Data Breach Report, incidents involving biometric and personal data incur some of the highest costs, averaging $4.45 million per breach. Furthermore, a global survey conducted by Accenture revealed that 87% of citizens are concerned about the handling and storage of their biometric data within centralised systems, indicating a growing trust deficit.
From an architectural standpoint, centralised machine learning systems face limitations in cross-domain interoperability, scalability, and real-time responsiveness – capabilities that are essential for interconnected smart city ecosystems. Challenges such as data silos, inconsistent standards, latency in authentication processes, single points of failure, and regulatory compliance barriers further impede the effectiveness and resilience of these systems. These challenges collectively underscore the pressing need for a decentralised, privacy-preserving identity framework that enables secure, scalable, and interoperable biometric authentication. Emerging technologies such as blockchain and federated learning offer promising solutions by decentralising identity management, enhancing privacy through local data processing, and enabling cross-sector collaboration without compromising data sovereignty. This special session aims to address these challenges and explore cutting-edge research and practical implementations that leverage decentralized technologies to enhance the trust, transparency, and resilience of biometric systems in smart cities.
Organizers:
- Dr. Sujit Biswas, University of London, UK
- Prof. Kashif Sharif, Beijing Institute of Technology, China
- Prof. Ashok Kumar Pradhan, SRM University, AP, India
- Prof. Md Atiqur Rahman Ahad, University of East London, UK