Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2
Quick Answer
This paper shows that The Membership Inference Test (MINT) Demo 2 framework enhances transparency in machine learning by determining if specific data was used in training models.
Quick Take
Achieving up to 90% accuracy with a popular face recognition model and four state-of-the-art , it offers a web platform for auditing various models, promoting compliance with AI regulations.
Key Points
- MINT achieves up to 90% accuracy in detecting training data.
- Framework tested on a popular face recognition model and four LLMs.
- Comprehensive web platform integrates MINT, aMINT, and gMINT technologies.
- Promotes AI transparency and compliance with emerging regulations.
- Supports auditing across diverse image and text databases.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2606. 14748v1 Announce Type: new Abstract: We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes. MINT is a technique for experimentally determining whether specific data were used during machine learning model training. We establish the theoretical framework and propose multiple architectures for MINT depending on the amount of information known about the models that are being audited.
Experimental results using a popular face recognition model, 4 state-of-the-art , and multiple, diverse, and large-scale public image and text databases achieve promising accuracy levels in the detection of training data of up to 90%. Building on these results, we introduce a comprehensive web platform1 that expands these capabilities to image and text modalities. The platform integrates a diverse technological stack, including MINT, aMINT, and gMINT, allowing users to audit a wide range of models.
This demonstrator aims to promote AI transparency and provides a practical tool to foster compliance with emerging AI regulations.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.