In recent years, brain fingerprint identification has emerged as a promising biometrics modality due to its potential for providing high security and precision in identity recognition. Leveraging the unique neural patterns that emerge during cognitive tasks, this method holds particular promise for applications in high-security environments, such as defense, healthcare, and finance. In this chapter, an advanced brain network-based approach is proposed for multi-task and single-session brain fingerprint identification. The methodology begins with the construction of brain functional networks by calculating phase synchronization values between electroencephalography (EEG) channels, which allows for the capture of intricate brain activity patterns. Following this, a range of network metrics, such as node degree, clustering coefficient, and global efficiency, are computed to generate a comprehensive and multidimensional feature vector, effectively representing the complex dynamics of brain function. To ensure robust classification, Linear Discriminant Analysis (LDA) is employed to process these extracted features, enabling precise brain fingerprint identification with high accuracy. The proposed method is rigorously evaluated across four diverse datasets that encompass a wide array of cognitive tasks, providing a comprehensive testbed for evaluating the method’s effectiveness. Experimental results demonstrate that the method achieves an average identification accuracy exceeding 95% across all datasets, with a peak accuracy of 99%. These findings highlight the method’s robust potential for real-world brain fingerprint identification applications, illustrating its efficacy in providing accurate and reliable identity recognition even in the context of diverse, multi-task environments.