{"data":{"id":"07381de6-0f00-4e6f-a4d2-32610e39fecc","title":"Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging","summary":"Researchers propose a detection framework for adversarial attacks on deep neural networks used in radiological imaging. The method analyzes Sigmoid function variations and compares prediction differences between clean and attacked images, using random-noise attacks to identify adversarial perturbations. It reached up to 99.8% accuracy in identifying adversarial directional attacks across three medical datasets, including Chest X-Ray Images for Classification, Retinal Fundus Multi-disease Image Dataset and Brain Tumor Dataset.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.15628v1","publishedAt":"2026-10-11T13:58:26.000Z","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":"2026-10-11T13:58:26.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}