AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Asymmetric Anchoring: Opening the Black Box of MLLMs for Forgery Detection

Zhiqiang Yang, Renshuai Tao, Chunjie Zhang, Zhaoxiang Liu, Xiaolong Zheng, Yao Zhao

ECCV 2026 · Large language models › Language, safety and interpretability · approach: Text watermarking

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 anchoring representation loss L_arl on real images (ablation)LLaVA-v1.5-7B + CLIP · SID-Set detectionaccuracy: 91.78% -> 96.60%Improved
add L_arl with SigLIPv2 encoder (ablation)Vicuna-1.5-7B + SigLIPv2 · SID-Set detectionaccuracy: 93.21% -> 97.04%Improved
add L_arl (ablation)LISA-7B-v1 · OpenSDID SD1.5 (in-domain)accuracy: 91.17% -> 90.25%Hurt
add L_arl (ablation)LISA-7B-v1 · OpenSDID SDXLaccuracy: 77.65% -> 85.00%Improved
add L_arl to a 13B LLM (ablation)Vicuna-1.5-13B + CLIP · SID-Set detectionaccuracy: 94.13% -> 97.24%Improved
apply L_arl asymmetrically (real only) instead of to real and tampered (ablation)AAP-lisa · SID-Setlocalization IoU: 40.2 -> 56.8Improved
apply L_arl asymmetrically (real only) instead of symmetric (ablation)AAP-lisa · SID-Setdetection accuracy: 94.8 -> 97.1Improved
inject alignment error map into the localization decoder (ablation)AAP-lisa · Localization (avg of OpenSDID and SID-Set)IoU: 41.52 -> 50.25Improved
inject error map on SID-Set only (ablation)AAP-lisa · SID-Setlocalization IoU: 43.80 -> 56.85Improved
add anchoring (AAP) to reduce representation driftMLLM fine-tuning · Real vs Tampered featuresinter-class distance: 5.4550 -> 13.2344Improved
use AAP versus SIDA for real image recognitionAAP-lisa · SID-Set (Real)accuracy: 89.1 -> 97.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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