Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67682
Volume:
10 |
10 |
Oct 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Master of Computer Applications
Godavari Institute of Management and Research (GIMR), Jalgaon, Maharashtra, India.
The exponential growth of advanced generative artificial intelligence and deep learning models has revolutionized digital content creation, while simultaneously introducing severe security challenges through hyper-realistic image forgery, deepfakes, and manipulated visual media. These synthetic media threats undermine public trust, compromise digital journalism, and threaten legal and forensic integrity. Traditional verification methods are often inadequate against sophisticated diffusion-based generation techniques that leave minimal visible traces. To combat this evolving challenge, this project presents AI Lens, an innovative, next-generation image authentication and forensic system engineered to detect digital manipulation with exceptional precision and reliability. AI Lens implements a robust dual-tier forensic architecture combining client-side hardware metadata inspection with advanced deep vision transformer models and spectral analysis. The system thoroughly evaluates structural anomalies, high-frequency Fourier grid irregularities, error level analysis, and invisible generative watermarks or signatures. Designed for seamless accessibility, it features a responsive, high-performance interface that delivers real-time authenticity scores, detailed diagnostic reports, and comprehensive forensic breakdowns. By empowering journalists, legal investigators, and everyday digital consumers with instant and accurate verification tools, AI Lens redefines media provenance, establishes trustworthy authentication standards, and effectively safeguards digital truth in an increasingly synthetic world.
KEYWORDS
In conclusion, this project successfully presents AI Lens, a novel and robust dual-tier image authentication system designed to combat the rising threat of advanced deepfakes and generative AI manipulations. By seamlessly integrating client-side EXIF metadata inspection and Error Level Analysis (ELA) with server-side Vision Transformers (ViT) and Fourier spectral evaluation, the system effectively bridges the gap between low-latency execution and high-precision detection. Experimental evaluations confirm that AI Lens achieves an exceptional classification accuracy of 98.4%, significantly outperforming conventional single-tier models. Ultimately, the system establishes a reliable, transparent, and scalable benchmark for digital forensics, safeguarding media provenance and restoring trust in visual content.
1. Exif.js Documentation (2024). JavaScript library for reading EXIF image metadata. 2. Google Gemini API Documentation (2026). Google AI for Developers Guide on Multimodal Vision Models and Asynchronous Request Handling. 3. MDN Web Docs (2026). HTML5 Canvas API, File API, and Modern JavaScript (ES6+) Guides. Mozilla Developer Network. 4. IEEE Xplore Digital Library. Research Papers on Digital Image Forensics, Error Level Analysis (ELA), and AI-Generated Deepfake Detection. 5. Springer & ACM Digital Library. Journal Articles on Computer Vision, Multimodal AI Evaluation, and Privacy-First Client-Side Web Applications.
Publication Date
10/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
13
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...