Initial commit

Add government ID proof-of-concept: Aadhaar/PAN/Voter ID number validation

Add Document/ID forensics: new detection pillar for AI-generated/tampered documents

Wire up video Fast Mode (CorefakeNet single-pass) end to end

Merge upstream/main: reconcile async-DB/FastAPI/React fork with ML methodology branch

Add classical ML tie-breaker + face-crop fix for face-swap blind spot

Add learned video temporal model (replaces heuristic TemporalAnalyzer)

Expand Fusion MLP from 4 to 7 inputs to include all trained models

Add BatchNorm to AudioDeepfakeCNN; fixes persistent dead-ReLU collapse

solvje the CI error

feat: Add Wav2Vec2 audio detector and CLIP ViT-L/14 image detector

feat: Add production infrastructure, CI/CD, Docker, tests, and implementation plan

feat: Add v2 architecture — FastAPI + Gradio, core pipeline, CorefakeNet, training suite

Integrate audio deepfake detection module into multimodal pipeline

Initial commit: AI Authenticity Checker