Digital Shadow Detector: An AI-Driven Framework for Detecting and Assessing Unintended Digital Footprints

Author

Mayuri Vhanmane, Amarja Jagtap, Manas Chavan,Harshada Jadhav, Rushika Burande

Abstract

 The rapid growth of social media, cloud services, mobile applications, online transactions, and connected devices has increased the amount of information that individuals unintentionally leave across the Internet. This collection of publicly observable, residual, and indirectly associated information is referred to in this paper as a digital shadow. A digital shadow can include exposed usernames, old profiles, public metadata, breached-account indicators, reused aliases, public documents, and relationships between seemingly unrelated digital identities. This paper proposes Digital Shadow Detector (DSD), a defensive cybersecurity framework that combines lawful open-source intelligence (OSINT), entity resolution, risk scoring, and optional machine-learning classification to discover and prioritize an individual's publicly exposed digital footprint. The framework is designed around privacy-by-design principles: it uses only authorized or publicly accessible data, avoids credential attacks, and presents evidence and remediation guidance rather than exploiting discovered information. A prototype architecture is described with an Android/web client, Python backend, search and collection layer, normalization engine, risk-analysis module, database, and reporting layer. Evaluation is proposed using precision, recall, F1-score, duplicate-resolution accuracy, scan latency, and risk-prioritization quality. The work provides a practical foundation for personal cybersecurity, digital-footprint awareness, and defensive security assessments.

Keywords

Digital Shadow, Digital Footprint, OSINT, Cyber Security, Entity Resolution, Risk Scoring, Machine Learning, Privacy, Threat Intelligence

Full Text:

Download Paper PDF

References

National Institute of Standards and Technology (NIST), Cybersecurity Framework (CSF) 2.0, 2024.

National Institute of Standards and Technology (NIST), Privacy Framework: A Tool for Improving Privacy through Enterprise Risk Management.

OWASP Foundation, OWASP Application Security Verification Standard (ASVS).

ENISA, Threat Landscape and cybersecurity risk-management publications.

Clarke, R., “Information Technology and Dataveillance,” Communications of the ACM, 1988.

Solove, D. J., “A Taxonomy of Privacy,” University of Pennsylvania Law Review, 2006.

Bishop, M., Computer Security: Art and Science, Addison-Wesley.

Stallings, W., Effective Cybersecurity: A Guide to Using Best Practices and Standards.

Share your valuable work from Social Media Buttons