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{198894,
        author = {Dhayalan K and Akshita K and Jerisha Flavio J and Kalaiselvi S and N. Sri Thejas},
        title = {Cross-Protocol Website Fingerprinting},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10934-10937},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198894},
        abstract = {This paper introduces a machine learning-based framework for fingerprinting TCP and QUIC traffic using Wireshark packet captures. The proposed approach extracts statistical and flow-level features from both encrypted and non-encrypted sessions to identify protocol-specific behaviors. A structured methodology involving AIM, PROCEDURE, OBSERVATION, and RESULT was adopted to ensure clarity and reproducibility. Experimental evaluation demonstrates that classifiers such as Random Forest and Support Vector Machine achieve high accuracy in distinguishing QUIC traffic patterns from TCP flows, even under encryption. The findings highlight the potential of combining protocol-level analysis with machine learning techniques to enhance traffic monitoring, anomaly detection, and cybersecurity in modern internet architectures.
In addition to achieving high accuracy in distinguishing TCP and QUIC traffic, the study highlights the practical applicability of machine learning based fingerprinting in real time monitoring environments. The integration of Wireshark captures with classifiers such as Random Forest and SVM not only demonstrated robustness against encrypted flows but also provided a scalable framework adaptable to institutional and organizational needs. These findings emphasize the relevance of combining statistical analysis with machine learning for modern network security and traffic management.},
        keywords = {Machine Learning, QUIC, TCP, Traffic Analysis, Wireshark.},
        month = {April},
        }