Hybrid RAG-Enhanced Deepfake Detection: A Novel Approach Combining Retrieval-Augmented Generation with Visual Inconsistency Analysis
Hybrid RAG-Enhanced Deepfake Detection: A Novel Approach Combining Retrieval-Augmented Generation with Visual Inconsistency Analysis
This research proposes a novel hybrid framework for deepfake detection that integrates Retrieval-Augmented Generation (RAG) with visual inconsistency analysis. The system utilizes a dual verification strategy: contextual verification using ViT and FAISS for semantic similarity, and AI-generated artifact detection using YOLO and SAM. It introduces uncertainty quantification and operates entirely offline for privacy, making it suitable for journalism, law, forensics, and personal content verification. This paper aims to contribute a scalable, interpretable, and privacy-preserving system for combating manipulated media in the age of generative AI.
Deepfake detection, RAG, Visual anomaly detection, Privacy-preserving AI, Uncertainty quantification, AI-generated media, Computer vision
Deepfake detection, RAG, Visual anomaly detection, Privacy-preserving AI, Uncertainty quantification, AI-generated media, Computer vision
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!