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{199853,
        author = {Shraddha Rajendra Bairagi and Shruti Pravin Bhangale and Aditya Dattatray Bhagwat and Asim Minaz Kazi and Archana L Rane and Pooja S Kurne},
        title = {Multi-Channel Phishing Detection Using Machine Learning, Deep Learning, and Behavioral Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15745-15752},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199853},
        abstract = {Phishing attacks have become more sophisticated over time, evolving from simple email scams into complex threats that operate across multiple communication channels. Today, attackers use platforms such as SMS, voice calls, social media, DNS, and QR codes to exploit both technical weaknesses and human behavior, making these attacks harder to detect and prevent. Traditional detection methods, which are often rule-based or focused on a single channel, struggle to keep up with these adaptive and AI-driven techniques.
This paper presents a systematic analysis of multi-channel phishing attacks and introduces an integrated detection framework that combines machine learning, deep learning,  and  behavioral  analysis.  The  study reviews recent research from 2023 to 2025 and examines phishing methods in terms of their attack strategies, technical complexity, and impact on user behavior. The results show that AI-driven phishing attacks can increase user compromise rates by 12–30%, while advanced detection models can achieve accuracy levels of up to 90% in controlled settings.
To address these challenges, a multi-layered framework is proposed that includes data collection, feature extraction, intelligent classification, and risk-based decision- making. The findings highlight the need to combine advanced technological solutions with  user  awareness  and  supportive  policies. Overall, this work aims to support the development of more adaptive, reliable, and scalable defenses against evolving phishing threats in modern digital environments.},
        keywords = {Phishing attacks, cybersecurity, multi-channel phishing, machine learning, deep learning, social engineering, artificial intelligence, behavioral analysis, phishing detection, cognitive bias, email phishing, SMS phishing, voice phishing, QR code phishing, and DNS-based attacks.},
        month = {April},
        }