{"data":{"id":"8d8021ec-bc6d-4fb1-be52-dde473831bef","title":"Unveiling the Backdoor’s Suppression Effect for Backdoor Defence","summary":"Researchers report that when a second backdoor is embedded into a deep neural network after an earlier one, the later backdoor suppresses the earlier one. Building on this, they propose Safedoor, a defensive backdoor embedded into suspect models using a small amount of data. Across eight representative backdoor attacks, Safedoor reduces the average attack success rate from 97.3% to 2.2%, while keeping clean-data accuracy high and adding 0.32% to inference time.","solution":"Safedoor: intentionally embed a later backdoor (Safedoor) into suspect DNNs that may already be infected, using the proposed efficient embedding algorithm.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11695233","publishedAt":"2026-09-17T13:32:35.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-09-17T13:32:35.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":null}}