{"data":{"id":"ac5ab386-f660-4a47-8b5a-75207cd05cce","title":"Backdoor as Probe: Test-Time Adversarial Defense for CLIP","summary":"Researchers propose Backdoor as Probe (BaP), a test-time adversarial defense for CLIP that repurposes backdoor trigger-to-target mechanisms. A defender-controlled probe is implanted via a closed-form edit to a selected MLP layer, responding weakly to clean inputs and strongly to adversarial activation shifts. Across 16 benchmarks, BaP raises average robust accuracy from 1.0% to 52.3% while keeping clean accuracy, with up to a 5.7x inference speedup.","solution":"BaP is the mitigation: a test-time defense that detects adversarial inputs via the probe's target-direction response, then selectively rectifies them by optimizing a small perturbation that steers representations toward the clean subspace.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2609.34641v1","publishedAt":"2026-09-28T08:53:23.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["CLIP"],"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":"2026-09-28T08:53:23.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}