PassGAT: A Graph Attention Network Framework for Device Authentication in AIoT-Enabled Supply Chain Risk Mitigation

In AIoT-enabled secure and green supply chain systems, robust device authentication measures are crucial to maintaining the integrity of the ecosystem. One key challenge in this context is mitigating password guessing attacks—a scenario that can be modeled as a specialized sequence prediction task demanding high character-level accuracy and computational efficiency to safeguard devices and data. Although natural language processing (NLP) models, particularly GPT-based approaches, have excelled in sequence prediction tasks, they often lack the precision needed for password guessing due to their reliance on broad contextual dependencies. To address these limitations, we propose PassGAT, a novel framework that leverages Graph Attention Networks (GAT) to enhance password prediction performance. PassGAT transforms passwords into graph representations, where each character is treated as a node, enabling selective computation of attention coefficients between characters. This approach captures both local dependencies essential for character-level accuracy and global patterns that enhance the understanding of password structures. Experimental results demonstrate that PassGAT achieves an average improvement of 15.58% in accuracy over an existing GPT-based password guessing model while reducing computational overhead by 85.19%. By significantly enhancing authentication accuracy and efficiency, PassGAT provides a robust and sustainable solution to mitigate password-related security risks in AIoT-enabled supply chain systems.