#membership-inference-attacks News & Analysis

2 articles tagged with #membership-inference-attacks. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBearisharXiv – CS AI · Jun 17/10

🧠

How does Bayesian Sampling help Membership Inference Attacks?

Researchers propose Bayesian Membership Inference Attacks (BMIA), a novel method that uses Bayesian sampling and Laplace approximation to detect whether specific data points were used in model training. The approach significantly reduces computational overhead compared to existing methods while achieving state-of-the-art attack performance across image, text, and tabular datasets.

AIBearisharXiv – CS AI · May 277/10

🧠

Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models

Researchers have developed SD-MIA, a black-box membership inference attack that can detect whether specific images were used in training diffusion-based image generation models by analyzing how the model denoise images and perturbed text instructions. This technique outperforms existing methods without requiring access to internal model features, raising significant privacy and copyright concerns for AI developers and users.