DeepTruth AI: A Multi-Modal Framework for Deepfake and Fake News Detection

Author(s)	Ms. Shreya Sunil Shinde, H. R. Vyawahare
Country	India
Abstract	Deepfakes and fake news pose serious threats to digital trust by spreading manipulated images, videos, audio, and textual information. This research presents DeepTruth AI, a multi-modal detection framework that integrates text, image, and audio analysis to identify synthetic and manipulated content with improved accuracy. The system employs BERT for textual encoding, CNNs for visual feature extraction, and LSTMs for audio modeling, combined through a transformer-based fusion mechanism. An explainability engine provides visual, textual, and audio-level attributions for transparent detection. The proposed framework also includes synchrony analysis to detect lip-sync inconsistencies. DeepTruth AI offers applications in media verification, cybersecurity, biometric authentication, and legal forensics, addressing challenges related to evolving deepfake generation technologies and real-time deployment.
Keywords	Deepfake Detection, Fake News Analysis, Multimodal Learning, Transformer Fusion, Explainable AI, Cybersecurity, Audio-Visual Synchrony
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-11-19
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.60997

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research