SecPO: Principled Adversarial Training for Prompt Injection Security

SecPO: Principled Adversarial Training for Prompt Injection Security. It centres on Meta, and also names Benchmarks and GitHub. Reported by arXiv. Bharat Hunt files it under AI Agents — the section covering autonomous and tool-using systems, agent frameworks, MCP and orchestration.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.