看见未被看见的:重新思考利用情境学习进行非法推广检测
Seeing the Unseen: Rethinking Illicit Promotion Detection with In-Context Learning
AI总结:
本文提出利用情境学习框架检测非法推广,通过减少标注数据实现高性能,具备跨平台泛化和自主发现新威胁的能力。
摘要:
非法在线推广是一个持续存在的威胁,不断进化以逃避检测。现有审核系统仍依赖平台特定的监督和静态分类法,是一种反应性范式,难以在不同领域通用或发现新威胁。本文系统研究了情境学习(ICL)作为统一框架用于非法推广检测。通过严格分析,我们显示,正确配置的ICL在使用22倍更少标注示例的情况下,性能可与微调模型相媲美。我们展示了三大关键能力:(1)泛化到未见过的威胁:ICL无需类别特定演示即可泛化到新的非法类别,大多数评估类别性能下降不足6%。(2)自主发现:一种新的两阶段流程将2900个自由形式标签提炼为连贯的分类法,揭示了八个之前未记录的非法类别,如高利贷和非法移民。(3)跨平台泛化:在搜索引擎和推特上部署200,000个真实世界样本,无需适应,ICL达到92.6%的准确率。此外,其唯一标记的样本中有61.8%对应于现有检测器遗漏的边缘或伪装内容。我们的发现将ICL定位为内容审核的新范式,结合专门分类器的精确性、跨平台泛化和自主威胁发现能力。通过转向推理时推理,ICL提供了一条通往主动适应审核系统的方法。
英文摘要:
Illicit online promotion is a persistent threat that evolves to evade detection. Existing moderation systems remain tethered to platform-specific supervision and static taxonomies, a reactive paradigm that struggles to generalize across domains or uncover novel threats. This paper presents a systematic study of In-Context Learning (ICL) as a unified framework for illicit promotion detection. Through rigorous analysis, we show that properly configured ICL achieves performance comparable to fine-tuned models using 22x fewer labeled examples. We demonstrate three key capabilities: (1) Generalization to unseen threats: ICL generalizes to new illicit categories without category-specific demonstrations, with a performance drop of less than 6% for most evaluated categories. (2) Autonomous discovery: A novel two-stage pipeline distills 2,900 free-form labels into coherent taxonomies, surfacing eight previously undocumented illicit categories such as usury and illegal immigration. (3) Cross-platform generalization: Deployed on 200,000 real-world samples from search engines and Twitter without adaptation, ICL achieves 92.6% accuracy. Furthermore, 61.8% of its uniquely flagged samples correspond to borderline or obfuscated content missed by existing detectors. Our findings position ICL as a new paradigm for content moderation, combining the precision of specialized classifiers with cross-platform generalization and autonomous threat discovery. By shifting to inference-time reasoning, ICL offers a path toward proactively adaptive moderation systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。