AI Paper Atlas

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

Rethinking Membership Inference Attacks for CLIP

Lluis Gomez

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 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
Use same-distribution (CommonPool) non-members instead of cross-dataset non-membersCSA, AEA, WSA, MCDropout attacks · CLIP-MIA-Bench vs cross-datasetAUC: MCDropout 98.27 -> 52.63; WSA 93.49 -> 50.07Hurt
Increase CLIP training set from 4M to 400M pairs (ablation)Cosine Similarity Attack · CLIP-MIA-BenchAUC: 94.1 -> 62.5 -> 51.1 (%)Hurt
Use white-box loss+grad-norm features instead of similarityMIA on CLIP 400M · CLIP-MIA-BenchAUC: 51.12 -> 53.48Improved

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