AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Hanqing Liu, Shouwei Ruan, Yao Huang, Shiji Zhao, Xingxing Wei

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 7 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
use ITA(best) optimized illumination instead of random illumination (ablation)ITA · COCO zero-shot (OpenCLIP ViT-B/16)top-1 accuracy: 71(↓26) -> 46(↓51)Improved
use ITA(best) instead of random illumination (ablation)ITA · COCO zero-shot (EVA-CLIP ViT-G/14)top-1 accuracy: 93(↓5) -> 84(↓14)Improved
use ITA(best) instead of random illumination (ablation)ITA · COCO VQA (LLaVA-1.5)correctness: 59.00 (↓9.00) -> 48.00 (↓20.00)Improved
use ITA(best) instead of random illumination (ablation)ITA · COCO captioning (OpenFlamingo)consistency: 66.37(↓3.85) -> 53.93(↓16.27)Improved
compare ITA with Shadow AttackITA(best) · COCO zero-shot (OpenCLIP ViT-B/16)top-1 accuracy: 84(↓13) -> 46(↓51)Improved
compare ITA with Natural Light AttackITA(best) · COCO zero-shot (OpenAI CLIP ViT-L/14)top-1 accuracy: 93(-) -> 51(↓42)Improved
larger encoder reduces ITA damageITA(best) · COCO zero-shottop-1 accuracy: 46(↓51) -> 84(↓14)Mixed
compare ITA captioning transfer to VLMsITA(best) · COCO captioning (LLaVA-1.5)consistency: 78.60 -> 63.73(↓14.87)Improved
add ITA transfer attack to VQAITA(best) · COCO VQA (OpenFlamingo)correctness: 45.00 -> 19.00 (↓26.00)Improved
optimize ITA(best) instead of random for naturalness (ablation)ITA · COCO naturalness GPT-4o sumnaturalness: 2.33 -> 2.15Hurt
optimize ITA(best) instead of random for DISTS (ablation)ITA · COCO naturalnessDISTS: 0.021 -> 0.051Hurt
increase optimization iterations to 200 (ablation)ITA · OpenCLIP attack success rateattack success rateImproved

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