{"data":{"id":"f916f91a-54d6-4c53-a03a-2654e9f2a85d","title":"Box-Free Model Watermarks are Prone to Black-Box Removal Attacks","summary":"Researchers show that box-free model watermarks, which protect deep learning image-processing models, can be removed even when the protected model and the watermark extractor are black boxes. They build three removers: an extractor-gradient-guided (EGG) remover for extractors using only ReLU activation, a gradient-estimating version for unknown extractors, and a transferable remover built on private proxy models for inaccessible extractors. The removers erase embedded watermarks while preserving processed image quality, and the EGG remover can also replace watermarks.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11495080","publishedAt":"2026-04-27T13:16:23.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-04-27T13:16:23.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","confidentiality"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":null}}