arXiv:2609.08445cs.LGcs.CR2026-09
在匿名嵌入空间中实现低延迟反欺诈，保护隐私。
Topological Fraud Detection in Latent Transaction Spaces
- 基于拓扑匿名嵌入，迭代进行无监督筛选与有监督定位
- 实现极低延迟的隐私保护可疑行为识别
- 适合金融风控、支付系统等对隐私敏感的场景
完全在拓扑匿名化的嵌入空间中进行欺诈检测，通过多轮无监督过滤和有监督精确定位，实现超低延迟的隐私保护初步筛查，使机构能够在不泄露个人身份信息的情况下识别可疑交易活动。
原文摘要 · Abstract (English)
Working entirely on topologically anonymized embeddings, we perform fraud detection using iterative rounds of unsupervised filtering followed by supervised sniping. The result is an ultra-low latency privacy--preserving triage that allows institutions to flag suspicious activity without compromising Personally Identifiable Information.
反欺诈隐私保护图神经网络
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。