Streamlining security auditing with generative AI
summary
Automates turning Security Hub findings into a filled incident runbook by piping events through EventBridge and Lambda, using Amazon Kendra to index org docs and Amazon Bedrock to generate a template-aligned response; demo shows a populated runbook template that includes exact AWS steps for EBS default encryption, evidence collection, and postmortem actions. Architecture supports severity filters, ticketing or channel notifications, and works as an automated first-draft authoring step rather than a final human-free remediation.
AI-written summary · about
chapters (7)
- 0:00Introduction and agenda
- 1:54Security auditing challenges
- 3:28Generative AI in security
- 5:05Defining response runbooks
- 6:06Technical architecture
- 10:24Real-life implementation
- 13:26Conclusion and next steps
related talks
47mCentralizing security at scale w/ Security Hub & Intuit’s experience
01h 02mSecuring data and democratizing the alert landscape
34mLayering AWS security services to automate incident response
24mAnalytics-based investigation & automated response
38mBuilding Security at Speed
55mStreamline security analysis with Amazon Detective
33mAutomating Cloud Security and Incident Response (DevSecOps)
24mAnalytics-based investigation & automated response