IRO Journals
Journal of Trends in Computer Science and Smart Technology

CAAMF: Conflict-Aware Adaptive Multimodal Fusion for QR Code Phishing Attack Detection

Open Access
Published: 15 July, 2026
Pages: 627-648
  • Nidhi Nigam , Nidhi Nigam
    Research Scholar, Department of Computer Science and Engineering, SAGE University, Indore, India
    Research Scholar, Department of Computer Science and Engineering, SAGE University, Indore, India
  • Rajat Bhandari Rajat Bhandari
    Professor, Institute of Advance Computing, SAGE University, Indore, India
    Professor, Institute of Advance Computing, SAGE University, Indore, India
view PDF
view PDF

How to Cite

Nigam, Nidhi, and Rajat Bhandari. 2026. “CAAMF: Conflict-Aware Adaptive Multimodal Fusion for QR Code Phishing Attack Detection”. Journal of Trends in Computer Science and Smart Technology 8 (3): 627-48. https://doi.org/10.36548/jtcsst.2026.3.010.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

QR Phishing Detection (Quishing)
Multimodal Security
Adaptive Fusion
Conflict-Aware Detection
UPI Payment
Enterprise Security

Abstract

QR codes are widely utilized in digital transactions; however, substantial security risks are increased by QR-based phishing (quishing) attacks. Existing attack detection techniques depend on a single modality-either analysis of URLs or visual inspection of QR codes causing high false-positive rates. Furthermore, attackers exploit mechanisms that bypass either of these techniques. This paper proposes CAAMF, a Conflict-Aware Adaptive Multimodal Fusion framework which combines different layers for URL risk assessment, visual integrity analysis, and conditional anomaly resolution into a unified pipeline. The URL scoring layer utilizes LightGBM with threat intelligence, the visual layer uses lightweight Convolutional Neural Networks (CNN) to detect tampering, and Isolation Forest acts as a conditional conflict resolver among disagreements between detection modalities. The results demonstrate an accuracy of 95.9 %, an AUC of 0.982, and a false-positive rate of 2.4 %, outperforming the evaluated baseline models. The conflict-aware adaptive fusion framework is significantly optimized for deployment in real-time (less than 25 ms inference) applications in UPI payment and enterprise security.

References

  1. Yalda, Rouwa, Arshad Khan, and Narayan Nepal. "B-PhishQR-A Blockchain-Based Framework for Secure QR Code Verification Against Phishing Attacks." Telematics and Informatics Reports (2026): 100289.
  2. Pricop, Emil, and Sanda Florentina Mihalache. "Quishing-A Review of QR Code Attacks and a Framework Design for Safe Scanning." In International Conference on Emerging Trends and Technologies on Intelligent Systems, Singapore: Springer Nature Singapore, 2025, 284-296.
  3. Nigam, Nidhi, and Rajat Bhandari. “Performance Analysis of QR Phishing Detection Approaches.” Journal of Information Systems Engineering and Management, vol. 10, no. 33s, 2025, 221–225.
  4. Ismail, Safwati, Mohammed Hazim Alkawaz, and Alvin Ebenazer Kumar. "Quick Response Code Validation and Phishing Detection Tool." In 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), IEEE, 2021, 261-266.
  5. Alsulami, Abdulaziz A., Qasem Abu Al-Haija, Badraddin Alturki, Ayman Yafoz, Ali Alqahtani, Raed Alsini, and Sami Saeed Binyamin. "Efficient Malicious QR Code Detection System Using an Advanced Deep Learning Approach." Computer Modeling in Engineering & Sciences 145, no. 1 (2025): 1117.
  6. Bekavac, Luka Jure Lars, Simon Mayer, and Jannis Strecker. "QR-Code Integrity by Design." In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 2024, 1-9.
  7. Aprillini, Nadeline, Jessica Seren Sutrisno, Jocelyn Marcella, and Franz Adeta Junior. "QR Code Phishing Detection: A Multi-Modal Ensemble Learning Framework Combining URL and Image Analysis." In 2025 5th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), IEEE, 2025, 387-391.
  8. Kustiawan, Yanche Ari, and Khairil Imran Ghauth. "PhishOFE: A Novel Machine Learning Framework for Real-Time Phishing URL Detection with Optimized Feature Engineering." IEEE Access (2025).
  9. Alageel, Almuthanna, and Sergio Maffeis. "Hawk-Eye: Holistic Detection of Apt Command and Control Domains." In Proceedings of the 36th annual ACM symposium on applied computing, 2021, 1664-1673.
  10. Sahoo, Doyen, Chenghao Liu, and Steven CH Hoi. "Malicious URL Detection Using Machine Learning: A Survey." arXiv preprint arXiv:1701.07179 (2017).
  11. Jin, Dongzi, Yiqin Lu, Jiancheng Qin, Zhe Cheng, and Zhongshu Mao. "SwiftIDS: Real-Time Intrusion Detection System Based on LightGBM and Parallel Intrusion Detection Mechanism." Computers & Security 97 (2020): 101984.
  12. Y. Ari Kustiawan and K. I. Ghauth, "Evaluating the Impact of Feature Engineering in Phishing URL Detection: A Comparative Study of URL, HTML, and Derived Features," in IEEE Access, vol. 13, 2025, 126756-126768. doi: 10.1109/ACCESS.2025.3579223
  13. Alaca, Yusuf, and Yüksel Çelik. "Cyber Attack Detection with QR Code Images Using Lightweight Deep Learning Models." Computers & Security 126 (2023): 103065.
  14. Kamnounsing, Palakorn, Karin Sumongkayothin, Prarinya Siritanawan, and Kazunori Kotani. "Adversarial Halftone QR Code." IEEE Access 12 (2024): 126729-126737.
  15. Sarkhi, Mousa, and Shailendra Mishra. "Detection of QR Code-Based Cyberattacks Using a Lightweight Deep Learning Model." Engineering, Technology & Applied Science Research 14, no. 4 (2024): 15209-15216.
  16. Minocha, Arshia, Aman Goyal, and Rashmi Gandhi. "Recognition of Valid QR Codes with Machine Learning." In 2024 IEEE 13th International Conference on Communication Systems and Network Technologies (CSNT), IEEE, 2024, 724-730.
  17. Ford, Jason, and Hala Strohmier Berry. "Feasibility of Machine Learning-Enhanced Detection for QR Code Images in Email-based Threats." In 2024 Cyber Awareness and Research Symposium (CARS), IEEE, 2024, 1-9.
  18. Rivas, Luis, Varun Kumar Singh, Vinayak Khandelwal, and Lanier Watkins. "Securing QR Codes Infrastructure Using AI to Detect Malicious Activity." In 2025 IEEE 15th annual computing and communication workshop and conference (CCWC), IEEE, 2025, 0076-0083.
  19. Wairagade, Anant, and Sumit Ranjan. "User Behavior Analysis for Cyber Threat Detection: A Comparative Study of Machine Learning Algorithms." In 2025 13th International Symposium on Digital Forensics and Security (ISDFS), IEEE, 2025, 1-6.
  20. Njuguna, David, and John G. Ndia. "Quick Response Code Security Attacks and Countermeasures: A Systematic Literature Review." (2025), 1–20.
  21. Hadi, Mohannad Hossain, and Karim Hashim Al-Saedi. "Adaptive Hybrid Learning for Advanced Phishing Detection." In AIP Conference Proceedings, vol. 3207, no. 1, AIP Publishing LLC, 2024, 030001.
  22. Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou. "Isolation Forest." In 2008 eighth ieee international conference on data mining, IEEE, 2008, 413-422.
  23. OpenPhish, "Phishing Intelligence Feed," 2024. [Online]. Available: https://openphish.com
  24. “PhishTank | Join the Fight Against Phishing.” [Online]. Available: https://www.phishtank.com
  25. Alsuhibany, Suliman A. "Innovative QR Code System for Tamper-Proof Generation and Fraud-Resistant Verification." Sensors 25, no. 13 (2025): 3855.
  26. URLhaus, "Malware and Phishing URL Repository," https://urlhaus.abuse.ch/ 2025
  27. Ozkan-Okay, Merve, Erdal Akin, Ömer Aslan, Selahattin Kosunalp, Teodor Iliev, Ivaylo Stoyanov, and Ivan Beloev. "A Comprehensive Survey: Evaluating the Efficiency of Artificial Intelligence and Machine Learning Techniques on Cyber Security Solutions." IEEe Access 12 (2024): 12229-12256.
  28. Chen, Tianqi, and Carlos Guestrin. "Xgboost: A Scalable Tree Boosting System." In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, 785-794.
  29. Benign and Malicious QR Codes https://www.kaggle.com/datasets/samahsadiq/benign-and-malicious-qr-codes