{"data":{"id":"37f5cfcc-200d-4163-b5e1-eabebf0c552b","title":"ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning","summary":"ATLAS is a query-based framework that discovers sets of adversarial inputs for black-box learning systems by casting attack generation as an active learning level set estimation problem. Under a limited query budget, it recovers more of the adversarial region than prior work in toy experiments, and on standard and adversarially trained MNIST, CIFAR, and ImageNet targets it produces more representative attacks than NES, SignHunter, and BayesOpt. The authors present it as an automated red-teaming framework for analyzing robustness and continuous auditing.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.07323v1","publishedAt":"2026-10-05T19:56:17.000Z","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":"2026-10-05T19:56:17.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}