Code Security Reinvented Navigating the era of AI
summary
Six practical ways to use AI for security with 14 Copilot demos and concrete outcomes: use AI to propose fixes rather than rely on it for detection, combine deterministic scanners with AI-suggested patches, and run supply‑chain checks via a multi‑file prompt set. Demoed nondeterminism and hallucinations in issue detection, showed fixed 600 vulnerabilities in two weeks (fix rate from 50% to 100%) via Copilot autofix, flagged MCP server concerns (Kodasi, GitHub), and published a playground repo (gh.iose io/secure codegame).
AI-written summary · about
chapters (9)
- 0:00Introduction to AI security
- 0:26AI for safer code writing
- 3:40Detection vs fixing problems
- 6:52MCP protocol explained
- 9:39Supply chain security decisions
- 12:50Security guidance for projects
- 14:59AI for fuzzing automation
- 16:43Fixing security issues with autofix
- 20:40Summary and resources
related talks
41mCode Security Reinvented Navigating the era of AI
38mCode Security Reinvented: Navigating the era of AI
32mCode Security Reinvented: Navigating the Era of AI
58mSecuring Code in the Age of AI
30mWhat Are the Security Risks Associated with AI-Generated Code? 🤔
28mAI-Generated Code: Unmasking the Security Pitfalls
26mSmarter Code, Sneakier Risks: Supply Chain Security in the Age of AI
46mBreaking AI: Live coding and hacking applications with Generative AI