用二维签名提升图像异常检测速度与准确率
2DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signatures
- 基于粗糙路径理论构建二维签名嵌入的半监督框架
- 在对抗攻击下检测精度更高，计算耗时显著降低
- 适合需要实时防御的图像安全系统部署
机器学习技术的快速发展引发了模型安全问题，尤其在训练阶段（投毒）和测试阶段（逃避、伪装、逆向）面临威胁。执行图像任务的模型易受对抗攻击，导致性能下降并产生不良结果。本文提出一种名为2DSig-Detect的新方法，利用二维签名嵌入的半监督框架，基于粗糙路径理论实现图像异常检测。我们在训练时和测试时的对抗场景中验证该方法，并与现有最先进方法进行对比。实验表明，2DSig-Detect在检测对抗扰动方面表现出更优性能，同时大幅降低计算时间。
原文摘要 · Abstract (English)
The rapid advancement of machine learning technologies raises questions about the security of machine learning models, with respect to both training-time (poisoning) and test-time (evasion, impersonation, and inversion) attacks. Models performing image-related tasks, e.g. detection, and classification, are vulnerable to adversarial attacks that can degrade their performance and produce undesirable outcomes. This paper introduces a novel technique for anomaly detection in images called 2DSig-Detect, which uses a 2D-signature-embedded semi-supervised framework rooted in rough path theory. We demonstrate our method in adversarial settings for training-time and test-time attacks, and benchmark our framework against other state of the art methods. Using 2DSig-Detect for anomaly detection, we show both superior performance and a reduction in the computation time to detect the presence of adversarial perturbations in images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。