{"data":{"id":"c67dc51f-135c-4ba0-81b8-4505b8fefa45","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","summary":"Large language models (LLMs, which are AI systems trained on vast amounts of text) are vulnerable to serious attacks like hallucinations (making up false information), jailbreaks (tricking the AI into ignoring its safety rules), and backdoors (hidden malicious instructions inserted during training). This research proposes a detection method using hidden state forensics (analyzing the internal numerical patterns that flow through the model's layers) to identify abnormal or malicious behavior in real-time, achieving over 95% accuracy with minimal computational cost.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11480194","publishedAt":"2026-04-13T13:17:12.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","model_poisoning"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["Large Language Models (general)"],"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":"2026-04-13T13:17:12.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":"peer_reviewed","atlasIds":null}}