{"data":{"id":"9dabcaf1-9b64-4438-a941-4c4c0b9fad28","title":"Poisoned truth: The quiet security threat inside enterprise AI","summary":"AI data poisoning is a security threat where an AI model's training data or information sources become corrupted, causing the system to make decisions based on false information while appearing normal. This can happen through malicious attacks, but more often organizations poison their own systems by feeding AI models data from multiple conflicting sources like outdated files and incompatible databases. Unlike traditional cyberattacks that trigger visible alarms, poisoning is dangerous because no obvious damage appears, yet the AI produces plausible but incorrect answers affecting business decisions.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://www.csoonline.com/article/4166171/poisoned-truth-the-quiet-security-threat-inside-enterprise-ai.html","publishedAt":"2026-05-06T09:01:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning","rag_poisoning"],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["SANS Institute","Berryville Institute of Machine Learning","BlackFog"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-05-06T09:01:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}