AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Your Prompts Are Not Safe: Output-Free Membership Inference via Prompt Vectors in Vision-Language Tuning

Yuran Bian, Xiaohan Zhang, Zhiyuan Yu, Changqing Li, Li Pan

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 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 contrastive learning-based feature projector (ablation)PIPRA · MIA on 9 datasets (avg)AUC and accuracy: avg about +7.3% AUC, +6.7% accuracyImproved
add contrastive projector (ablation)PIPRA · Caltech101AUC: 88.0 -> 92.4Improved
add contrastive projector (ablation)PIPRA · Food101AUC: 74.6 -> 86.0Improved
add contrastive projector (ablation)PIPRA · Flowers102accuracy: 75.8 -> 76.2No clear effect
use mismatched surrogate model instead of matching target model (ablation)PIPRA · Caltech101accuracy: ViT-B/32 100.00 -> RN50 surrogate 75.07Hurt
use a shadow dataset from a different domain (ablation)PIPRA · Caltech101accuracyMixed
use PIPRA (output-free, prompt only) instead of output-dependent MIAsPIPRA · nine datasetsAUC: 79.7 -> 87.6 (avg vs Gradient-based)Improved

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