{"data":{"id":"25287f0d-84d2-4c73-9bd9-c6ad7cea87b3","title":"SecPO: Principled Adversarial Training for Prompt Injection Security","summary":"The SecPO paper addresses prompt injection, where instructions in untrusted data manipulate an AI agent. It argues that Meta-SecAlign's DPO-based training anchors to an insecure reference model and uses weak simulated attacks, and proposes a SecPO loss plus an adversarial training pipeline that synthesizes strong injections (best@240). On Qwen3.6-27B, the authors report AgentDojo ASR@800 of 8.8% versus 78.8% for Meta-SecAlign under AttackerMovesSecond, with no noticeable benign utility loss across nine benchmarks.","solution":"The proposed defense is the SecPO loss combined with adversarial training (AT) on synthesized injected inputs; the authors release code, training data and a model at the linked GitHub and Hugging Face locations.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.41998v1","publishedAt":"2026-10-30T16:43:17.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Meta-SecAlign","Qwen3.6-27B","AgentDojo"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-30T16:43:17.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.97,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}