Detection of Sensitive Personal Data in Large Data Sets Using Ray with Deep Learning
summary
Describes using machine learning, deep learning and NLP together with Spark and Ray to detect sensitive personal data at petabyte scale, contrasting this with traditional rule-based data-protection and DLP methods and their limitations. Presents new algorithms and scaling techniques for running these models across large datasets and provides benchmarked accuracy and performance results for the proposed approach.
AI-written summary · about
related talks
24mBuilding Complex Data Analytics Pipelines with Ray
35mHow Bytedance Builds Large-Scale Data Processing Pipelines for Multimodal Models with Ray
35mOperating a Production-Scale Physical AI Data Platform with Ray
03mRay: A Distributed Execution Framework for Emerging AI Applications
22mRay, a Unified Distributed Framework for the Modern AI Stack
30mHow to Scale Unstructured Data Processing with Ray Data
31mNext-Generation Data Science Workflows Using Ray
22mGenerative AI Model Data Pre-Training on Kubernetes: A Use Case Study