{"data":{"id":"99ba4adf-64db-4998-9f6f-405b7fdf6f82","title":"BAPLe++: Cross-Model Transferability and Prompt-Level Defense of Backdoors in Medical Foundation Models","summary":"BAPLe++ studies whether backdoors implanted through prompt learning in medical foundation models (Med-FMs) transfer to other Med-FMs, measured with Clean Accuracy Difference (CAD) and Backdoor Accuracy Difference (BAD). The authors also propose DePLe, which uses the infected prompt as a fixed anchor and learns a new prompt on a small clean set to reduce backdoor accuracy. Across four Med-FMs and six chest X-ray and histopathology datasets, backdoors transferred asymmetrically and in a dataset-dependent manner, and DePLe reduced backdoor accuracy more consistently than four training-free input transformations.","solution":"DePLe: learn a new prompt on a small clean set, using the infected prompt as a fixed anchor, so the model keeps its clean task while diverging from the compromised embedding region, without retraining the backbone.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.10764v1","publishedAt":"2026-11-07T14:45:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Medical foundation models (Med-FMs)"],"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":"2026-11-07T14:45:37.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}