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
LLM privacyLLM securityData poisoning
Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning
This talk from ETH Zurich reveals how large language models (LLMs) pose significant, often overlooked, privacy risks through advanced profiling and introduces novel poisoning attacks that activate only after model quantization or fine-tuning.
Explore Insights →
Large Language Models (LLMs)Retrieval Augmented Generation (RAG)Adversarial Attacks
Cascading Adversarial Bias from Injection to Distillation in Language Models
RAG systems, designed to enhance LLM accuracy and personalization, are vulnerable to 'Phantom' trigger attacks where a single poisoned document can manipulate outputs to deny service, express bias, exfiltrate data, or generate harmful content.
Explore Insights →
Want more on machine learning vulnerabilities?
Explore deep-dive summaries and actionable takeaways from the best minds across different podcasts discussing this topic.
View All Machine Learning Vulnerabilities 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