Leave It To The Machines
summary
Claims that ML/AI can shift left security by automatically learning real cloud traffic and producing enforceable controls. Demonstrates a system that inspects CI/CD, Kubernetes namespaces, pods and serverless functions, models IAM and network flows, spots anomalies and blocks command and control on day one, and emits least‑privilege YAML snippet policies. Learning converges quickly (noted after one hour of learning), continuously relearns after deploys, and outputs concrete remediation steps rather than vague advice.
AI-written summary · about
chapters (4)
- 0:00Start
- 2:57Cloud Security Breaches
- 4:59Am I Still Relevant as a Security Person
- 7:18Build Microservices
related talks
12mKeynote: Leave it to the Machine - How to Leverage AI to Effectively Shift Left Sec...
32mAI/Machine Learning: What is Actually Working in Cybersecurity?
19mSecuring AI Pipelines from Development to Production
16mCloud security reimagined: The generative AI advantage
50mBuilding AI Security In: MLSecOps in Practice
26mRunning Secure AI/ML Experiment in a Unified MLOPS-DevSecOps Pipeline
44mAdvancing Cybersecurity with AI and Machine Learning: Opportunities and Challenges
39mThe Future of Cybersecurity in an AI-driven Era