AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

M$^4$I: Multi-modal Models Membership Inference

Pingyi Hu, Zihan Wang, Ruoxi Sun, Hu Wang, Minhui Xue

NeurIPS 2022 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion

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 feature-based instead of metric-based attackM4I · unrestricted scenario image captioningattack success rateImproved
restrict attacker to data-only knowledge (ablation)metric-based M4I · image captioningattack success rateHurt
attacker lacks architecture and dataset knowledge (constrained) (ablation)metric-based M4I · image captioningattack success rate: 81 -> 51% - 76%Hurt
attacker lacks architecture knowledge (ablation)feature-based M4I · image captioningattack success rateHurt
target trained on MSCOCOmetric-based M4I · image captioningattack success rateHurt
data augmentation and l2 regularization on targetM4I attacks · image captioningattack success rateMixed
differential privacy training with epsilon = 1.3M4I attacks · FR target modelattack success rateHurt
differential privacy training with epsilon = 1.3target captioning model · FR target modelaverage ROUGE-L: 0.245 -> 0.147Hurt

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