放射学中的对抗攻击:一项系统综述
该研究系统检索截至2023年4月的文献,纳入22项放射学对抗攻击研究,主要针对图像分类算法。部分攻击可将算法AUC降至0、成功率达100%。作者认为对抗攻击威胁目前更偏理论而非实际,但仍属潜在风险,需提高警惕、加强网络安全并推动伦理与法律指南制定。
要点
- 对抗攻击主要针对放射图像分类算法,部分攻击可将AUC降至0、成功率达100%。
- 22项研究中14项评估白盒攻击、3项黑盒攻击、5项两者兼有。
- 攻击威胁目前更偏理论而非实际,但仍属潜在风险。
核心结论
- 对抗攻击是日益增长的担忧,当前威胁更偏理论而非实际,但仍代表潜在风险。
- 需警惕此类攻击、加强网络安全措施并影响伦理与法律指南的制定。
研究设计与样本
- 系统综述,检索MEDLINE与Google Scholar截至2023年4月的放射学对抗攻击研究。
- 共纳入22项研究,发表时间为2018年3月至2023年4月,主要聚焦图像分类算法。
诊断标准与关键数值
- 14项研究评估白盒攻击,3项评估黑盒攻击,5项两者均研究。
- 11/22项针对胸部X线分类算法,其余涉及胸部CT(6/22)、脑MRI(4/22)、乳腺X线(2/22)、腹部CT(1/22)、肝脏超声(1/22)和甲状腺超声(1/22)。
- 部分攻击高度有效,可将算法性能AUC降至0,成功率达100%。
临床应用与阅片要点
- 原文结论提出应警惕对抗攻击、加强网络安全措施并推动伦理与法律指南制定,以确保深度学习技术在医学中的安全使用。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: The growing application of deep learning in radiology has raised concerns about cybersecurity, particularly in relation to adversarial attacks. This study aims to systematically review the literature on adversarial attacks in radiology.
METHODS: We searched for studies on adversarial attacks in radiology published up to April 2023, using MEDLINE and Google Scholar databases.
RESULTS: A total of 22 studies published between March 2018 and April 2023 were included, primarily focused on image classification algorithms. Fourteen studies evaluated white-box attacks, three assessed black-box attacks and five investigated both. Eleven of the 22 studies targeted chest X-ray classification algorithms, while others involved chest CT (6/22), brain MRI (4/22), mammography (2/22), abdominal CT (1/22), hepatic US (1/22), and thyroid US (1/22). Some attacks proved highly effective, reducing the AUC of algorithm performance to 0 and achieving success rates up to 100 %.
CONCLUSIONS: Adversarial attacks are a growing concern. Although currently the threats are more theoretical than practical, they still represent a potential risk. It is important to be alert to such attacks, reinforce cybersecurity measures, and influence the formulation of ethical and legal guidelines. This will ensure the safe use of deep learning technology in medicine.
引用
- Sorin V, Soffer S, Glicksberg BS, et al. Adversarial attacks in radiology - A systematic review. Eur J Radiol. 2023. PMID: 37699278. doi:10.1016/j.ejrad.2023.111085
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。