{"data":{"id":"44977d8c-5ddc-43e0-a03b-b3a343299922","title":"AEGIS: Real-Time Latent-Space Backdoor Detection for Dependable and Secure Small Language Model Inference","summary":"AEGIS is a non-invasive runtime framework that detects backdoor-induced anomalies in transformer hidden states without retraining the protected model. It monitors equidistant internal layers, compresses their pooled activations into a 64-dimensional latent space, and flags inputs by cosine distance from a clean-data centroid. Across Mistral-7B, Qwen2.5-7B, a QLoRA-backdoored Qwen2.5-1.5B and a BadNets-backdoored Vision Transformer, it reports AUROC values of 0.95 to 1.00 and prefill detection latency of 0.47 to 2.40 ms.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://doi.org/10.3390/technologies14100636","publishedAt":"2026-10-02T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","model_poisoning"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Mistral-7B","Qwen2.5-7B","Qwen2.5-1.5B","Vision Transformer"],"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":"2026-10-02T00:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":null}}