{"data":{"id":"d840ac74-7dfe-4c07-bbee-7cf2021b22b6","title":"Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin","summary":"This study tests six large language models with 400 adversarial prompts in Yoruba and Nigerian Pidgin, scored by native-speaker annotators. Models that rejected up to 69% of English prompts rejected as few as 0% in Yoruba, largely because they failed to understand the prompts rather than being safer. Attack success rates rose for most models in the Nigerian languages, showing that English-centric safety alignment does not transfer to these languages.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.39590v1","publishedAt":"2026-10-29T08:30:29.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Google"],"affectedVendorsRaw":["GPT-4o Mini","Gemini 2.0 Flash","Aya 101"],"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":"2026-10-29T08:30:29.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}