{"data":{"id":"6780b074-f6d1-445a-aa99-6a24babed946","title":"Preventing Model Extraction in Contextual Linear Optimization","summary":"This paper studies how an attacker who submits context queries to a predict-then-optimize system can extract its underlying linear prediction model from the returned decisions alone. The authors combine inverse optimization with boundary sampling in an adaptive attack, then propose a defense that perturbs decisions only when the predicted cost vector lies near a decision boundary. Experiments on synthetic and real data show the defense increases extraction error at a measurable cost in performance.","solution":"The proposed mitigation is a defense mechanism that perturbs decisions only when the predicted cost vector is near a decision boundary. The source states a regret bound in terms of the perturbation radius and a lower bound on expected extraction error for attackers that fit defended responses.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.29918v1","publishedAt":"2026-10-21T15:55:08.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_theft"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-10-21T15:55:08.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}