How srijansundaram/deepshield works
DeepShield analyzes images and videos through a Streamlit interface or REST API, returning model verdicts and forensic evidence. The image path combines an ensemble detector with face analysis and advisory forensic signals; the video path adds frame-level, temporal, audio-visual, and identity checks. Results can be visualized, explained, logged, or exported as PDF. The README also documents URL analysis, batch scans, and Grad-CAM. Some wiring is supported only by the SOURCE INDEX or README; unsampled implementation details are not inferred.
Main entry points: app.py Streamlit App · api.py REST API · video_utils.py Video Analysis · face_utils.py Face Analysis
Components 16
User Interfaces
- Streamlit App
app.py - REST API
api.py
Detection & Forensics
- Ensemble Detector
models/detector.py - Face Analysis
utils/face_utils.py - Image Forensics
utils/forensics.py - Compression Handling
utils/social_compression.py
Video Analysis
- Video Analysis
utils/video_utils.py - Audio-Visual Sync
utils/av_sync.py - Identity Tracking
utils/identity_consistency.py
Results & Reporting
- Signal Explainability
utils/explainability.py - Charts & Heatmaps
utils/visualize.py - Session History
utils/history.py - PDF Reports
reports/pdf_report.py
Other components
- User
- API Client
- Public Image URL
Connections 18
- User → Streamlit App: uses
README.md - API Client → REST API: submits analysis
README.md - Streamlit App → Ensemble Detector: analyzes images
app.py - Streamlit App → Face Analysis: analyzes faces
app.py - Face Analysis → Ensemble Detector: predicts faces
utils/face_utils.py - Streamlit App → Image Forensics: computes signals
app.py - Streamlit App → Compression Handling: adjusts artifacts
app.py - Streamlit App → Video Analysis: analyzes video
app.py - Video Analysis → Audio-Visual Sync: analyzes sync
utils/video_utils.py - Video Analysis → Identity Tracking: tracks identity
utils/video_utils.py - REST API → Ensemble Detector: analyzes input
api.py - REST API → Face Analysis: analyzes faces
api.py - Streamlit App → Signal Explainability: ranks signals
app.py - Streamlit App → Charts & Heatmaps: renders charts
app.py - Streamlit App → Session History: records sessions
app.py - Streamlit App → PDF Reports: exports reports
app.py - Public Image URL → Streamlit App: provides image
README.md - Streamlit App → API Client: returns results
README.md