Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196931,
        author = {Srikavi S and Obugayathri O and Priyadharshini TR and Gomathi A},
        title = {Explainable Multi-Modal Phishing Detection Using Lightweight Deep learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11359-11365},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196931},
        abstract = {Phishing attacks continue to pose a serious threat to online security by exploiting both deceptive URLs and manipulated webpage content. Many existing detection approaches rely on single-source features or complex models that lack transparency and are difficult to de-ploy in real-time environments. To address these chal-lenges, this paper presents a lightweight and explainable multi-modal framework for phishing detection. The proposed system combines structural URL characteris-tics with relevant webpage content features to capture a more complete representation of phishing behaviour. A computationally efficient deep learning model is utilized to ensure faster prediction with reduced resource con-sumption. In addition, a feature selection process is applied to eliminate redundant information and en-hance model performance. To improve trust and inter-pretability, an explainable AI mechanism is incorpo-rated to highlight the key factors influencing classifica-tion decisions. The experimental evaluation demon-strates that the proposed approach achieves better ac-curacy and lower false positive rates compared to con-ventional techniques. The system is designed for practi-cal deployment and can be effectively used in real-time cybersecurity applications such as browser-based pro-tection tools.},
        keywords = {Phishing Detection, Multi-Modal Learning, Explainable AI, Lightweight Deep Learning, URL Analysis, Cyber-security},
        month = {April},
        }