SOURCE-LINKED INTELLIGENCE
SecPO: Principled Adversarial Training for Prompt Injection Security
Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation. The existing best-defended LLM, Meta-SecAlign, is trained with the DPO loss but still suffers from attack success rates (ASRs) approaching 100% under adaptive prompt injections. One reason is that DPO anchors the model around the undefended reference model, which is insecure. We show an idealized reference model---an injection-invariant, utility-preserving oracle---can nevertheless be approximated, as its output distribution in trai
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-30T16:43:17.000Z
First collected: 2026-11-02T10:21:21.339Z. This is not the publication date.