Keywords
Concept bottleneck model
Explainable AI
Printing method detection
Human-machine collaboration
Submitted : 2026-01-14
Accepted : 2026-01-29
Published : 2026-02-13
Abstract
With the increase in cross-border mobility, passports, as critical identity documents, require robust anti-counterfeiting security. While existing deep learning-based automatic detection methods achieve high accuracy, they lack interpretability. This paper introduces the Concept Bottleneck Model (CBM) to construct a transparent passport printing method detection framework. By defining interpretable intermediate concepts and integrating linear reasoning, the model significantly enhances reliability and debugging efficiency. The article systematically analyzes the advantages, challenges, and future directions of this approach.
References
Weeraratna T, 2024, Beyond Borders: The Art and Science of Detecting Travel Document Forgeries. International Journal of Forensic Sciences, 9(4): 1–4.
Mohit M, 2016, The Evolution of Deep Learning: A Performance Analysis of CNNs in Image Recognition. International Journal of Advance Research in Education and Technology, 3(6): 2029–2038.
Stropeni A, Enhancing Interpretability in Visual Anomaly Detection Through Concept Bottleneck Models, thesis, University of Padua.
Dhillon A, Verma G, 2020, Convolutional Neural Network: A Review of Models, Methodologies and Applications to Object Detection. Progress in Artificial Intelligence, 9(2): 85–112.
Shafik W, 2026, The “Black Box” Problem: Lack of Transparency in AI Decision-Making. Springer: 167–186.
Srivastava D, Yan G, Weng L, et al., 2024, VLG-CBM: Training Concept Bottleneck Models with Vision–Language Guidance. Advances in Neural Information Processing Systems, 37: 79057–79094.