arXiv cs.CY· Wenbo Gao, Songbai Tan, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Yunyun Yang, Ming Li, Xiaofeng Zhu·· 11 小时前AI 评分38
ORACLE：从流式应用使用中的部分轨迹预判诈骗
ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage
AI 导读
ORACLE 是首个从流式应用使用轨迹中提前预判诈骗的智能体框架，可在诈骗意图明确前发出预警。团队构建了覆盖 12 种诈骗类型、95 个应用、平均跨度 15 天的真实长周期基准，并提出自演化上下文管理器与 on-policy 自蒸馏方案以整合碎片化证据、提升对早期潜在信号的敏感度。实验显示其在真实流式场景中持续改善早期诈骗预判，及时预警的同时减少误报。
正文 · 原文
Abstract:Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires anticipating scams before the intent becomes explicit. This is inherently challenging, as decisions must rely on partial trajectories with temporally distributed evidence. In this paper, we propose \textbf{ORACLE} Online Reasoning for Anticipating Cross-temporal Latent thrEats, the first agentic framework for early scam anticipation from \textit{streaming app-usage} trajectories. To support this setting, we curate a real-world long-horizon benchmark of streaming app-usage trajectories, covering 12 scam types, spanning extended periods (15 days on average), involving diverse applications (95 apps), and interleaving normal and scam behaviors. To address fragmented evidence, we introduce a self-evolving context manager that adaptively consolidates entity-centric interactions over time, enabling more effective reconstruction of cross-temporal evidence from partial observations. To enhance sensitivity to latent early-stage signals, we propose an on-policy self-distillation scheme in which a teacher model, conditioned on summarized anti-scam reflections and clues by skills, supervises a student model without access to such reflections. This scheme thereby distills evidence-informed knowledge and improves recognition of emerging fraud patterns from partial trajectories. Experiments show that \method{} consistently improves early scam anticipation, yielding timely warnings while reducing false alerts in realistic streaming scenarios.
| Subjects: | Machine Learning (cs.LG); Computers and Society (cs.CY) |
| Cite as: | arXiv:2605.16363 [cs.LG] |
| (or arXiv:2605.16363v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16363 arXiv-issued DOI via DataCite |
Submission history
From: Wenbo Gao [view email]
[v1]
Sat, 9 May 2026 16:26:16 UTC (1,471 KB)
[v2]
Fri, 30 Oct 2026 09:41:07 UTC (2,345 KB)
来源：arXiv cs.CY · arxiv.org