AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Trustworthy Image Authentication using Forensic Knowledge Graphs

Tai Nguyen, Matthew Stamm

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-supervised fingerprint learning to the backbone (ablation)FKG · FKG-50Kdetection AUC: 0.72 -> 0.94Improved
add self-supervised fingerprint learning to the backbone (ablation)FKG · FKG-50Klocalization F1: 0.44 -> 0.94Improved
add pairwise similarity constraint to contrastive loss (ablation)FKG · FKG-50Ktype accuracy: 0.63 -> 0.87Improved
add global self-attention to local graph attention in FRPN (ablation)FKG · FKG-50Ktype accuracy: 0.57 -> 0.87Improved
add local graph attention to full self-attention in FRPN (ablation)FKG · FKG-50Ktype accuracy: 0.55 -> 0.87Improved
add Hungarian matching loss to contrastive loss (ablation)FKG · FKG-50Klocalization F1: 0.72 -> 0.94Improved
add contrastive loss to Hungarian loss (ablation)FKG · FKG-50Kdetection AUC: 0.81 -> 0.94Improved
add transformer reasoner instead of linear classifiers (ablation)FKG · FKG-50Ktype accuracy: 0.69 -> 0.87Improved
add random in-context examples to the VLM prompt (ablation)VLM justification · FKG-50Kcompleteness: 0.32 -> 0.51Improved
add chain-of-thought to random in-context examples (ablation)VLM justification · FKG-50Kcorrectness: 0.63 -> 0.70Improved
use ICR protocol instead of random examples with CoT (ablation)VLM justification · FKG-50Kcompleteness: 0.55 -> 0.85Improved
show forensic graph explanation alongside the verdictFKG · human trust study (30 participants)trust rating (1-5): 3.39 -> 4.53Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy