Google TechTalks

Google TechTalks

Differential PrivacyMachine LearningData PrivacyLarge Language Models (LLMs)Machine Learning SecurityData poisoningData SecurityPrompt EngineeringFine-tuningLarge Language ModelsPrivacy AuditingLLM securityFederated LearningAI EthicsAdversarial AttacksMembership Inference AttacksModel MemorizationDeep LearningMachine learning vulnerabilitiesSynthetic Data GenerationMachine Learning PrivacyRetrieval Augmented Generation (RAG)AI SecurityNatural Language ProcessingLanguage ModelsAI SafetyContinual CountingGenerative AIStreaming AlgorithmsApproximation AlgorithmsData MemorizationPrivacyPrivacy-Preserving Data AnalysisCopyright InfringementInformation Theory
Streaming Private Continual Counting via Binning
Differential PrivacyStreaming AlgorithmsContinual Counting

Streaming Private Continual Counting via Binning

This talk introduces 'binning,' a novel matrix structure that enables space-efficient streaming private continual counting by approximating complex factorizations with piecewise constant segments, often outperforming theoretical bounds.

Explore Insights →
Continual Release Moment Estimation with Differential Privacy
Differential PrivacyMoment EstimationStreaming Algorithms

Continual Release Moment Estimation with Differential Privacy

This research introduces a novel differentially private algorithm, Joint Moment Estimation (JME), that efficiently estimates both first and second moments of streaming private data with a 'second moment for free' property, outperforming baselines in high privacy regimes.

Explore Insights →

Want more on streaming algorithms?

Explore deep-dive summaries and actionable takeaways from the best minds across different podcasts discussing this topic.

View All Streaming Algorithms 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