{"data":{"id":"94fc127c-0ec0-46db-bafc-7cb4c35451db","title":"Towards Fine-grained and Robust Detection of Human-AI Co-authorship","summary":"The authors formulate a discrete-class text provenance framework that sorts human-AI co-authorship into distinct degrees of AI involvement, separating surface-level AI polishing from AI restructuring of discourse. They show that adversarial paraphrasing substantially degrades detectors trained only on benign data. Augmenting training data with adversarial paraphrases produces consistent robustness gains and good cross-generator transferability.","solution":"Augment detector training data with adversarial paraphrases generated by the state-of-the-art paraphrasing attack model.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2611.01427v1","publishedAt":"2026-11-01T02:10:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"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":"2026-11-01T02:10:37.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}