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{203203,
        author = {Junaid Ahmed Khan and Goudicherla Chinmayi Srija and Dr. B. Poornima and Dr. K. Sreekala},
        title = {InternGuard: Fake Internship Offer Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {12093-12101},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203203},
        abstract = {— Fraudulent internship offers emails targeting undergraduate students have increased significantly with the growth of online recruitment platforms. These emails often impersonate legitimate organizations and attempt to deceive students into paying registration fees, security deposits, or onboarding charges. This paper presents InternGuard, an intelligent multi-module system designed to detect fraudulent internship emails through a combination of email header forensics, machine learning-based content analysis, and website legitimacy verification. The proposed system evaluates SPF, DKIM, and DMARC authentication records to identify spoofed emails, while TF-IDF feature extraction and a Random Forest classifier are used to analyze email content. In addition, domain age and SSL certificate validation are performed to assess the credibility of embedded websites. Experimental evaluation showed that the Random Forest model achieved the best overall performance among the tested classifiers, obtaining an F1-score of 86.3% and a cross-validation accuracy of 85.26%. External validation on the EMSCAD dataset demonstrated reasonable generalization capability despite domain differences. The system was further evaluated using real-world fake internship emails collected from students, where it successfully identified multiple scam indicators and classified both emails as high risk. InternGuard also incorporates explainable risk scoring and rule-based scam phrase analysis to improve transparency and reduce false positives. The complete system is implemented as a Flask-based web application with an interactive user interface designed for practical student use.},
        keywords = {Fake Internship Detection, Phishing Email Analysis, Random Forest, TF IDF},
        month = {May},
        }