{"data":{"id":"c4882e2d-82d9-4ae6-8064-a939dfb4ccb0","title":"Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs","summary":"Researchers show that in edge-cloud split inference of multimodal LLMs, an honest-but-curious server can infer age, gender and race from the intermediate features it receives, even when raw images stay local. They propose a label-budgeted recovery curve to measure feature-level privacy, finding that Safe-LLaVA, which filters model responses, still lets a server recover 75-85% of unprotected leakage from transmitted features with 20 labeled samples per class.","solution":"N/A -- no mitigation discussed in source.","labels":["security","privacy","research"],"sourceUrl":"https://arxiv.org/abs/2610.32079v1","publishedAt":"2026-10-23T02:31:11.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["data_extraction"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Safe-LLaVA","LLaVA"],"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":"2026-10-23T02:31:11.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}