cs.CVNov 7, 2026

Beyond Real or Fake: A Dual-Channel Authenticity and Reasoning Protocol for Photographic Assessment

Authors: Xiaoxiao Li, Ruinan Jin, Lili Meng, Miaosen Wang, Athula Balachandran, Pei Cao

Organizations: Google · University of British Columbia · Vector Institute · Google DeepMind

Abstract

Forensic verification has converged on a binary "real vs. fake" label that confates fully synthetic, tampered, and AI-retouched images despite their very different consequences. We argue that GenAI manipulations decompose along two complementary channels: a camera channel of sensor fingerprints (destroyed by neural processing), and a semantic channel of scene-level coherence (disrupted by content edits). Each manipulation type leaves a distinctive two-channel signature. We instantiate this taxonomy in 2CAP (2-Channel Authenticity Protocol), pairing a contrastively-trained camera encoder with a frozen semantic encoder to serve two applications on a shared backbone: (i) four-class authenticity classification via cross-attention fusion with learnable reliability weights; and (ii) evidence generation, where an authentic image serves as a reference for a query and the two encoders produce per-channel alignment scores together with a patch-level saliency map. These signals are supplied as privileged context to a frozen Vision-Language Model (VLM) through an Observe-Generate-Refine loop, yielding explanations with localization without forensic fine-tuning. On a multi-source benchmark, 2CAP attains the best classification performance, including strong retouching detection where existing methods fail, and improves explanation quality.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Trustworthy Image Authentication using Forensic Knowledge Graphs

    Jun 22, 2026Tai D. Nguyen, Matthew C. StammImage Forgery DetectionDigital Image Forensics

  2. Explaining AI-Image Detection: What the Heatmap Actually Shows

    Jul 31, 2026Leonid Kuturin, Ilya Sotnikov, Mark Khusnutdinov +4Image Forgery DetectionDigital Image Forensics

  3. When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection

    May 26, 2026Jihyeon Kim, Sohee Kim, Soosan Lee +3AI-Generated Image Detection