Google TechTalks
Differential PrivacyMachine LearningData PrivacyLarge Language Models (LLMs)Large Language ModelsDeep LearningAI SafetyPrompt EngineeringMachine Learning SecurityData poisoningMembership Inference AttacksCopyright InfringementNatural Language ProcessingData SecurityFine-tuningPrivacy AuditingLLM securityFederated LearningEthics of AIAdversarial AttacksStochastic Gradient DescentMatrix FactorizationPrivacy AlgorithmsLower BoundsModel EvaluationImage GenerationModel MemorizationMachine learning vulnerabilitiesSynthetic Data GenerationMachine Learning PrivacyRetrieval Augmented Generation (RAG)AI SecurityLanguage ModelsContinual CountingGenerative AIStreaming AlgorithmsApproximation AlgorithmsData MemorizationPrivacyPrivacy-Preserving Data AnalysisInformation Theory
Large Language ModelsAI SafetyMachine Unlearning
Atomic Facts to Structured Knowledge: Rethinking Unlearning & Jailbreaking in Large Language Models
This talk reveals how the interconnected nature of knowledge within Large Language Models creates fundamental vulnerabilities, enabling sophisticated jailbreaking attacks and undermining current unlearning methods.
Explore Insights →
Large Language Models (LLMs)Data MemorizationCopyright Infringement
Evaluating Data Misuse in LLMs: Introducing Adversarial Compression Rate as a Metric of Memorization
This presentation introduces Adversarial Compression Rate (ACR) as a robust metric to quantify LLM memorization, addressing copyright concerns by focusing on the shortest prompt needed to elicit exact verbatim output.
Explore Insights →
Want more on model evaluation?
Explore deep-dive summaries and actionable takeaways from the best minds across different podcasts discussing this topic.
View All Model Evaluation 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