Using edge models to find sensitive data (Practical AI #273)
Jun 13, 2024
auto_awesome
Join Ramin from Tausight as he discusses deploying edge AI models to search through billions of records for sensitive data. They explore challenges in securing PHI, detecting dark PHI, and using AI in an edge environment. Discover the potential of AI in healthcare and the importance of protecting sensitive data.
Tausight uses AI to detect sensitive PHI data in various formats.
Healthcare breaches often involve third-party partners, not just organizations themselves.
Deep dives
Emerging Threats in PHI Breaches
Personal Health Identifiable (PHI) data is highly targeted by hackers due to containing valuable information such as medical history, social security numbers, and insurance details. PHI breaches have significantly increased, with 133 million healthcare data breached in 2023, translating to one out of every three Americans being affected.
Methods of Data Breach and Impact
78% of PHI breaches result from network hacking, while other breaches occur through stolen devices or phishing attacks. Surprisingly, only 30% of incidents are directly from healthcare organizations, with the remaining 70% linked to third-party partners. Breaches exceeding a certain threshold result in public disclosure, fines, and damage to brand reputation.
Challenges in Healthcare Security
Healthcare organizations face difficulties in detecting 'dark PHI,' unstructured data containing personal health information. Current tools rely on pattern matching like regex, making detection of hidden data challenging. The healthcare sector grapples with unstructured data formats and the limitations of traditional detection methods.
AI Applications for PHI Protection
Talsight employs AI to detect sensitive data in unstructured content without relying on predefined patterns. The emphasis is on recognizing PHI in various data formats, irrespective of file extensions. Tailored AI models are optimized for edge deployment, enabling real-time monitoring and protection against PHI breaches.
We’ve all heard about breaches of privacy and leaks of private health information (PHI). For healthcare providers and those storing this data, knowing where all the sensitive data is stored is non-trivial. Ramin, from Tausight, joins us to discuss how they have deploy edge AI models to help company search through billions of records for PHI.
Changelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack.
Backblaze – Unlimited cloud backup for Macs, PCs, and businesses for just $99/year. Easily protect business data through a centrally managed admin. Protect all the data on your machines automatically. Easy to deploy across multiple workstations with various deployment options.