{"id":"seebug-paper-d31f8b9964eb","seq":1577358,"kind":"news","title":"融合谱特征与激活聚类用于医疗影像模型后门检测：方法、实现与评估","url":"https://paper.seebug.org/3519","permalink":"https://vulnpulse.app/items/seebug-paper-d31f8b9964eb","summary":"作者：Suresh Tamang 原文链接：https://arxiv.org/pdf/2609.14290v1 摘要 机器学习模型正越来越多地部署于医疗影像流程中，用于辅助诊断，而针对这些模型的训练期攻击已成为一个被明确点名的行业级关切：医疗行业指南将模型投毒与对抗攻击列为需要专门防御措施的威胁，而联邦政策则指示将扩展的人工智能漏洞检测工具提供给农村医院等关键基础设施运营方。谱特征分析（spec...","severity":null,"techs":[],"cves":[],"tags":[],"source":{"id":"seebug-paper","name":"Seebug Paper (Knownsec 404)"},"published_at":"2026-09-15T08:31:35.000Z","fetched_at":"2026-10-27T09:57:34.907Z"}