Merge pull request #79 from abinaze/feature/calibration-polish

Fix: relax tiny image confidence assertion — PRNU may return non-zero confidence

Fix: s[score] → s['score'] (NameError), fix cached_download → hf_hub_download

feat: Calibration, dedup fix, signal tests

Merge pull request #78 from abinaze/feature/dct-frequency

feat:DCT Frequency Artifact Detection (25th signal)

Merge pull request #77 from abinaze/feature/metadata-forensics

feat:Deep Metadata Forensics signal (24th signal)

Merge pull request #76 from abinaze/feature/ela-signal

feat:ELA (Error Level Analysis) signal (23rd signal)

Fix: unescaped quotes in Select Image button onclick attribute

Merge pull request #75 from abinaze/fix/frontend-bugs-and-security

fix: frontend bugs, security deps, cleanup unused files

Merge pull request #74 from abinaze/fix/security-dependency-updates

Fix: update safetensors 0.4.1→0.4.5 and accelerate 0.25→1.7.0 for transformers 4.53 compat

Fix: update huggingface_hub 0.20.0 → 0.30.0 to satisfy transformers 4.53.0

fix: update all vulnerable dependencies (Dependabot alerts)

Merge pull request #73 from abinaze/feature/prnu-signal

Fix: update test assertions for v1.1 and 4 detection methods

feat: PRNU camera fingerprint signal (22nd detection signal)

Fix: PDF download broken JS condition (data/processed/*.csv → data/processed/*.csv)

Merge pull request #72 from abinaze/feature/phase5-pdf-report

feat: Phase 5 — court-ready PDF report download button

Merge pull request #71 from abinaze/feature/phase4-evidence-ui

feat: show evidence_id on every analysis result in frontend

Merge pull request #70 from abinaze/feature/phase4-frontend-security

feat: Phase 4 — evidence_id in UI, fix 42 security vulnerabilities

feat: Phase 3 — audit log, analysis history API, evidence_id in UI

Fix: restore all missing imports in image_forensics.py (PIL, datetime, etc)

Fix: restore missing 'from typing import Dict, Any' in image_forensics.py

Fix: rebuild CLIP database with more balanced real/AI samples

feat: add evidence_id to every forensic report, fix duplicate import

feat: add unique evidence_id to every forensic report

Merge branch 'main' of https://github.com/abinaze/VeriFile-X

Fix: ensemble skips DIRE when unavailable, redistributes weight to statistical+CLIP

Update README.md

docs: complete advanced README with all features and architecture

Fix: restore HuggingFace YAML header in README

Fix: restore HF Space README yaml header + fix startup timeout

Fix: DIRE returns confidence 0.0 on failure so ensemble ignores it

Fix: rebuild CLIP database with balanced real/AI samples

Fix: add GitHub Pages and HF Space to default CORS origins

Fix: remove static.yml — was overwriting GitHub Pages with repo root instead of frontend/

feat: full UI showing all 21 signals, hashes, EXIF, tampering + fix API URL

Update copyright holder in LICENSE file

Fix: use libgl1 instead of libgl1-mesa-glx (Debian trixie)

Fix: add libGL and libglib for opencv-python in Docker

Deploy: fix HuggingFace API URL

Deploy: add Dockerfile for HuggingFace Spaces

Deploy: GitHub Pages via GitHub Actions