AI Threat Screening for 5G UPF with Automated Risk Mitigation
summary
Claims an AI-driven multi-risk scoring system that scores each UPF session from five signals: behavioral, geographic, temporal, volumetric and historical intelligence. It ingests real-time traffic and telemetry including EDR/CDR, applies an API-first containerized GitOps deployment with OpenTelemetry, and enforces policies via a tiered automated mitigation pipeline (traffic shaping → isolation → termination) plus automated rule suggestion. Reported outcomes are reduced alert fatigue and faster, scalable mitigation; rollout starts with baseline learning then gradual automation.
AI-written summary · about
chapters (10)
- 0:00Introduction and Speaker Disclaimer
- 0:55Understanding 5G Network Security Challenges
- 1:15Identifying Key Threats in 5G Networks
- 2:24Introduction to AI-Driven Multi-Risk Scoring Framework
- 3:05Behavioral Analysis and Risk Scoring
- 4:50Real-Time Threat Detection and Response
- 7:19Operational Benefits for DevOps Teams
- 8:30Integration with DevOps Workflows
- 9:08Getting Started with AI-Driven Security Operations
- 10:39Conclusion and Q&A
related talks
11mAI-Powered Cybersecurity in the Age of Advanced Threats
28mAI Under the Hood: Unmasking Hidden Threats
15mAI Security Simplified: Turning Complexity into Cohesion
06mAI Security for Kubernetes: Guardrails, Red Team, and Remediate
44mAI Meets Cybersecurity: Boosting Speed Without Losing Control
14mEnhancing Enterprise Security with AI
12mAI Risk Assessment for Cloud-Native SMBs
17mHarnessing AI for Autonomous Threat Defense in Multi-Cloud Security