Journal of Computers, Mechanical and Management

PDF

Cite article

Rights and permissions

N. Soni, R. Poonia, Adversarial OSINT detecting manipulation in public data for reliable investigations, Journal of Information and Communications Technology: Algorithms, Systems and Applications, 2026, 2(1), 26305 doi: https://doi.org/10.64189/ict.26305.

Rights and permissions

© The Author(s) 2026.

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as appropriate credit to the original author(s) and the source is given by providing a link to the Creative Commons License and changes need to be indicated if there are any. The images or other third-party material in this article are included in the article's Creative Commons License, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons License and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this License, visit: httpshttps://creativecommons.org/licenses/by-nc/4.0/

Abstract

Open-source intelligence (OSINT) has emerged as a critical component of digital investigations, particularly in domains such as cybercrime, national security, and fraud detection. However, the increasing prevalence of adversarial technologies, including deepfakes, synthetic text, social bots, and data poisoning, poses significant challenges to the reliability and integrity of OSINT. These malicious, nondefensive interventions contribute to what is termed adversarial OSINT, where manipulated or fabricated information undermines trust in open-source data. This study examines the evolving threat landscape associated with adversarial manipulation and proposes a multilayered detection framework to enhance OSINT reliability. The framework integrates computational analysis, digital forensic techniques, and cross-source verification mechanisms to identify and mitigate manipulated content effectively. Additionally, the research explores the dual role of simulated data, deepfakes, and controlled virtual environments, highlighting how they can be leveraged constructively to test and strengthen OSINT validation systems. Furthermore, the paper addresses key ethical, legal, and privacy considerations essential for the responsible deployment of OSINT methodologies. The findings emphasize that maintaining OSINT integrity requires a hybrid approach that combines automated detection techniques with human expertise and oversight. This integrated strategy ensures more robust, transparent, and trustworthy intelligence generation in adversarial environments.

Keywords:

• Open-source intelligence
• Adversarial attacks
• Digital forensics
• Misinformation detection
• Deepfake analysis
• AI security.

Graphical Abstract

Novelty statement

This study proposes a novel hybrid adversarial OSINT detection framework integrating multi-modal analysis and human-in-the-loop validation, improving detection accuracy and reliability in complex misinformation environments.