让人脸识别系统知道自己的能力边界，避免误判未知攻击
Confidence Aware Learning for Reliable Face Anti-spoofing
- 用高斯分布建模真实人脸和已知攻击，通过马氏距离评估置信度
- 在未知攻击场景下识别低置信样本，提升检测可靠性
- 适合对安全性要求高的身份认证场景
当前人脸反欺诈（FAS）模型在遇到未知场景或新型欺骗攻击时，往往过度自信，带来严重安全隐患。为此，本文提出自信感知的面部活体检测模型（CA-FAS），能够识别自身能力边界，实现可靠活体判断。为使模型‘知晓未知’，我们为真实人脸和已知攻击分别构建高斯分布，通过样本与两类分布间的马氏距离评估预测置信度。同时引入基于马氏距离的三元组挖掘方法，联合优化模型与高斯分布参数。大量实验表明，该模型能有效识别低置信样本，在超出其可靠范围的样本上进行过滤，显著优于其他FAS模型的可靠性表现。
原文摘要 · Abstract (English)
Current Face Anti-spoofing (FAS) models tend to make overly confident predictions even when encountering unfamiliar scenarios or unknown presentation attacks, which leads to serious potential risks. To solve this problem, we propose a Confidence Aware Face Anti-spoofing (CA-FAS) model, which is aware of its capability boundary, thus achieving reliable liveness detection within this boundary. To enable the CA-FAS to "know what it doesn't know", we propose to estimate its confidence during the prediction of each sample. Specifically, we build Gaussian distributions for both the live faces and the known attacks. The prediction confidence for each sample is subsequently assessed using the Mahalanobis distance between the sample and the Gaussians for the "known data". We further introduce the Mahalanobis distance-based triplet mining to optimize the parameters of both the model and the constructed Gaussians as a whole. Extensive experiments show that the proposed CA-FAS can effectively recognize samples with low prediction confidence and thus achieve much more reliable performance than other FAS models by filtering out samples that are beyond its reliable range.
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。