Srinivasa Rao Chalamala received his doctorate in Electronics and Communication Engineering (ECE). His research work was supervised by Prof. Yegnanaryana. Here’s a summary of his research work on Security and Protection of Facial Biometrics Systems:
Biometrics are physical and behavioral traits, which are unique and specific to individuals. Some of the widely used physical traits include face, fingerprint, iris, and behavioral traits include voice, signature, typing rhythm, and gait. Identifying a person based on any of the physical and behavioral traits is referred to as biometric authentication.
Biometrics authentication can be more convenient and secure than passwords, because biometric traits are relatively fixed and cannot be easily stolen or shared. But biometrics cannot be recovered and deemed to have been lost forever when compromised. Attackers try to subvert biometric systems and gain unauthorized access to digital and physical assets. Attacks on biometric systems can be classified into impersonation attacks and obfuscation attacks. These attacks are the result of the following biometric vulnerabilities (i) A compromised template database can be exploited by the attacker either, to replace a template with an imposter template or, to present a stolen template directly to the matching module, (ii) Invertible transform function could lead to estimation of biometric features, which can be used to create a physical fake or spoof of the biometric, (iii) Higher false accept rate can be exploited by the attacker to impersonate a victim user, (iv) Finally, biometric systems are sensitive to carefully crafted perturbations to the input biometric data. These perturbations can be used for impersonation attacks, as well as obfuscation attacks.
Researchers proposed several template protection methods to overcome some of the above vulnerabilities of biometric systems and also to defend against adversarial attacks. A template protection method converts an original template into a protected template in a non-invertible manner, intending to protect the biometric identifier even if a template is stolen. An ideal template protection mechanism must meet the following requirements: (i) Security or non-invertibility, (ii) Revocability, (iii) Diversity, (iv) Matching performance.
This thesis addresses some of these issues and proposes methods for facial template protection and for defending adversarial attacks on facial verification systems. The following studies are conducted in this thesis. (i) A modular Siamese network based method is proposed to improve the robustness of the face verification systems against adversarial attacks and simultaneously provide interpretability. In this approach, facial feature representations for each of the individual facial parts such as eyes, nose and mouth are learned in latent space though feature disentanglement. (ii) A template protection method based on deep neural networks is proposed, to improve the security of the biometric template without compromising on the matching performance. Another deep neural networks based template protection method is proposed, for which ancillary data is derived from the adversarial perturbations, (iii) A random projection based approach proposed for improving the non-invertibility of facial feature vectors, to prevent the reconstruction of biometric features, (iv) A novel facial feature descriptor based on local binary patterns has been proposed for face recognition, (v) Federated learning for face recognition and its security and privacy implications are explored.
March 2023