{"data":{"id":"b39c8005-09ae-4cb7-a95e-f855c16338a9","title":"Pixel-Adaptive Purification: From Uniform to Spatially Heterogeneous Noise Injection","summary":"Diffusion-based adversarial purification removes attacks by adding noise and then denoising, but uniform noise either over-corrupts clean regions or under-purifies perturbed ones. This research proposes a pixel-adaptive noise schedule guided by an SNR map, with an automatic stopping criterion and a two-stage latent optimization module. Experiments on CIFAR-10, CIFAR-100, SVHN, and ImageNet report that it outperforms representative adversarial training and purification methods under most attacks, including a stronger adaptive white-box setting, while keeping high standard accuracy.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11783068","publishedAt":"2026-11-09T05:03:07.000Z","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":"2026-11-09T05:03:07.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":null}}