{"data":{"id":"d6eb9b96-b674-477a-938e-7e22e491ec68","title":"Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift","summary":"Researchers test whether 73 no-reference image quality metrics for underwater images agree with human preferences, using five reference sets and a new paired-comparison study. No metric consistently matches people; the best worst-case Cohen's kappa is 0.23 (Q-Align), while two raters agree with a median kappa of 0.41, and UCIQE often favors edits people reject. The authors also release TrustUIQA, a benchmark pairing human references, study choices, edited and generated images, and scores for every metric on every image.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.18429v1","publishedAt":"2026-11-13T17:10:13.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Q-Align","UCIQE","Nano Banana Pro"],"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":"2026-11-13T17:10:13.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.75,"researchCategory":"preprint","atlasIds":null}}