{"data":{"id":"639a8044-4ac9-4341-b748-b8a8f5f45533","title":"Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing","summary":"Researchers study \"polarity blindness,\" a failure where LLMs miss harmful intent after grammatical negation or antonym replacement, using synonym replacement as a control. They test 260 prompts across 10 LLMs in English, Spanish and Czech, rated on a validated 0-5 harm scale, and whether an adversarial textual wrapper amplifies the effect. Polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable one, and it persists across typologically different negation systems.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.27908v1","publishedAt":"2026-10-20T09:22:50.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-20T09:22:50.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}