AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

PACO: Stabilizing Vision Embeddings along Local Paths for Robust Vision-Language Models

Qihang Tang, Jiacheng Pi, Zhiguo Yang, Xu Liu, Perley Xu, Wenjie Ruan

ECCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 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
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Captioning avg, APGD-Ensemble 2/255, LLaVA-7BCIDEr: 44.0 -> 50.3Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · VQA avg, APGD-Ensemble 2/255, LLaVA-7Baccuracy: 28.4 -> 30.1Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Captioning avg, APGD-Ensemble 4/255, LLaVA-7BCIDEr: 30.5 -> 35.3Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · VQA avg, APGD-Ensemble 4/255, LLaVA-7Baccuracy: 19.5 -> 20.9Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Targeted attack 8/255, avg CIDErCIDEr: 70.8 -> 80.1Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Targeted attack 8/255, success rateattack success rate: 3.2% -> 0%Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Zero-shot classification avg, cleanaccuracy: 58.7 -> 61.1Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Zero-shot classification avg, 2/255accuracy: 41.7 -> 45.8Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Zero-shot classification avg, 4/255accuracy: 28.9 -> 31.7Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · COCO image-to-text retrievalRecall@1: 5.3 -> 7.1Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · Flickr30K image-to-text retrievalRecall@1: 15.4 -> 18.6Improved
replace Sim-CLIP fine-tuning with PACOPACO vs Sim-CLIP · POPE mean F1F1: 76.9 -> 77.8Improved

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