Improving code security analysis with AI/ML
summary
Announces Amazon CodeGuru Security launching in preview with a claim of much lower false‑positive rates by retraining models on Amazon’s internal code; scans Java, Python and JavaScript, integrates via API with GitHub/Bitbucket/GitLab/CodePipeline/Inspector and IDEs (Visual Studio, IntelliJ, Jupyter), tracks bugs across revisions, and generates downloadable Code Fixes patches. Dashboard shows per‑pipeline counts (demo shows ~596 open, 600–700 recently closed). Preview is free and invites customer feedback.
AI-written summary · about
chapters (11)
- 0:00Introduction and agenda
- 1:49False positives in security tools
- 4:18How CodeGuru Security reduces false positives
- 7:09Introducing Amazon CodeGuru Security
- 9:14CodeGuru Security integrations
- 11:03Demo of CodeGuru Security dashboard
- 13:31GitHub integration walkthrough
- 14:15Automated code fixes feature
- 15:16XML Entity Detector demo
- 16:17Pipeline-specific vulnerability insights
- 17:01Closing and call for feedback
related talks
54mKeeping your code secure
41mCode Security Reinvented Navigating the era of AI
38mCode Security Reinvented: Navigating the era of AI
41mBake Security into your workflow with GitHub Advanced Security and AI
32mCode Security Reinvented: Navigating the Era of AI
59mUsing AI for Secure Code Creation: Enhancing Software Security
58mSecuring Code in the Age of AI
35mBring the power of machine learning to your developer operations