Google TechTalks
Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
This research introduces B-min-sep subsampling, a novel method that enhances privacy amplification for differentially private matrix factorization (DPMF) by leveraging correlated noise and enabling practical application in complex multi-attribution settings.
Differentially Private Table-Image Multimodal Data Generation
This research introduces DP-TabImage, a novel differentially private framework for generating synthetic multimodal data (tables and images) that preserves both individual data fidelity and cross-modal correlations, significantly outperforming existing methods.
Disparate Privacy Risks from Medical AI - An Investigation into Patient-level Privacy Risk
Medical AI models, especially larger ones, expose individual patient data to significant and disproportionately high privacy risks, particularly for minority patient groups, despite appearing safe in aggregate metrics.
How Much Do Language Models Memorize?
Meta researcher Jack Morris introduces a new metric for 'unintended memorization' in language models, revealing how model capacity, data rarity, and training data size influence generalization versus specific data retention.
Want more on deep learning?
Explore deep-dive summaries and actionable takeaways from the best minds across different podcasts discussing this topic.
View All Deep Learning Episodes→Don't see the episode you're looking for?
We're constantly adding new episodes, but if you want to see a specific one from Google TechTalks summarized, let us know!
Submit an Episode