{"data":{"id":"2de0b40e-0aa0-410a-9413-34c6ae295f01","title":"Multi-Layer Honeypot Framework for Defending Pre-Trained Language Models Against Backdoor Attacks in Classification Tasks","summary":"The Multi-Layer Honeypot (MLH) framework is a defense for pre-trained language models against backdoor attacks in text classification. It deploys honeypot modules across the lower, middle and higher layers during fine-tuning, aggregates layer-wise anomaly scores, and down-weights highly anomalous samples in the task loss. Experiments on SST-2, SMS, AGNews and Amazon Reviews with BERT, RoBERTa, XLNet, OPT-1.3B and LLaMA-7B report reduced attack success rates while keeping classification performance.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11740714","publishedAt":"2026-10-19T13:17:05.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["BERT","RoBERTa","XLNet","OPT-1.3B","LLaMA-7B"],"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":"2026-10-19T13:17:05.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":null}}