面向鲁棒医疗AI系统的对抗感知架构设计
Adversarially-Aware Architecture Design for Robust Medical AI Systems
AI总结：
本研究针对医疗AI面临的对抗攻击风险，通过皮肤病数据集实验验证威胁严重性与现有防御的局限性，提出需结合技术、伦理与政策构建更鲁棒公平的医疗AI。
摘要：
对抗攻击对医疗领域应用的AI系统构成严重风险，能够误导模型产生危险的错误分类，进而延误治疗或导致误诊。这类攻击通常难以被人类感知，会威胁患者安全，对医疗资源不足人群的影响尤为突出。本研究通过在一个皮肤病数据集上开展实证实验探究了此类漏洞，实验中对抗方法会显著降低分类准确率。通过详细的威胁建模、实验基准测试与模型评估，我们既证明了该威胁的严重性，也验证了对抗训练、蒸馏等防御手段能取得部分成效。结果显示，尽管防御手段能降低攻击成功率，但必须在防御效果与模型在干净数据上的性能之间取得平衡。我们最后呼吁整合技术、伦理与政策层面的方法，以构建更具韧性、更公平的医疗AI。
英文摘要：
Adversarial attacks pose a severe risk to AI systems used in healthcare, capable of misleading models into dangerous misclassifications that can delay treatments or cause misdiagnoses. These attacks, often imperceptible to human perception, threaten patient safety, particularly in underserved populations. Our study explores these vulnerabilities through empirical experimentation on a dermatological dataset, where adversarial methods significantly reduce classification accuracy. Through detailed threat modeling, experimental benchmarking, and model evaluation, we demonstrate both the severity of the threat and the partial success of defenses like adversarial training and distillation. Our results show that while defenses reduce attack success rates, they must be balanced against model performance on clean data. We conclude with a call for integrated technical, ethical, and policy-based approaches to build more resilient, equitable AI in healthcare.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
