How to protect generative AI models using GenAI Secure
summary
GenAI Secure ships as a serverless, in-account protection stack (deploys in ~5–6 minutes) that scans S3/EBS/EFS/FSx and other storage for malware and sensitive data, quarantines offending objects to a quarantine bucket, and supports inbound and outbound flows. Scans run in ECS Fargate tasks using multiple engines (CrowdStrike, Sophos, ClamAV) and integrates with Amazon Bedrock to produce malware analysis reports and generate regex data‑loss rules. No customer data leaves the account; 30‑day marketplace trial available.
AI-written summary · about
chapters (6)
- 0:00Introduction and philosophy
- 2:39The case for native security
- 5:17Architecture and product growth
- 8:56Event-based security scanning
- 10:44GenAI protection workflows
- 13:40Bedrock integration and closing
related talks
40mSecure Your GenAI Applications
40mSecuring Generative AI: Is it all an Illusion?
30mSecureAI: A Scalable, Secure, and Compliant AI Solution
44mGenerative AI Security — A Practical Guide to Securing Your AI Application
09mSecuring Generative AI Workloads
27mSafeguarding Generative AI Applications: Navigating Security Challenges and Best Pract...
43mSecurity of GenAI & LLMs: A New Era of Ethical Hacking
42mSecuring the Invisible