自包含数据清洗框架：无需污染比例即可净化异常检测训练集
Self-contained Data Cleaning for Unsupervised Anomaly Detection
做异常检测的同学应该会遇到训练集混入脏数据的问题。这篇论文的做法挺巧：用自编码器早期重建的余弦相似度找出污染点再删掉，不需要提前知道污染比例，8 个模型 10 个数据集上 F1 平均涨了 11.2%，而且是数据层面清洗，换模型也能用。
一篇 arXiv 论文提出面向无监督异常检测的自包含预处理框架，解决训练数据被恶意样本污染的问题。现有鲁棒方法通常需要预先知道污染比例，而这一信息在真实安全运营中很难获得。
该方法的技术路径是：在自编码器训练早期动态分析每个数据点与其重建之间的余弦相似度，将数据点映射到一个异常区域自然呈现低密度的动态空间，随后执行“硬清洗”，把识别出的异常候选全部从训练池移除。由于清洗发生在数据层面，其安全性与可靠性提升可无缝迁移到各种下游检测架构，不依赖特定模型。
作者在 8 个模型和 10 个安全相关数据集上做了评估，最高实现 100% 污染消除，F1 分数平均提升 11.2%，分类准确率平均提升 7.3%。
Self-contained Data Cleaning for Unsupervised Anomaly Detection
Training datasets for unsupervised anomaly detection are often assumed to be anomaly-free, but in practice, they frequently contain malicious or anomalous contamination. This contamination severely degrades the dependability and security of downstream detection models. While some contamination-robust methods exist, they rarely generalize across different model architectures and typically rely on a priori knowledge of the contamination ratio\textemdash information that is rarely available in real-world security operations. In this paper, we propose a novel, self-contained preprocessing framework for anomaly detection that identifies and removes training set contamination without relying on known contamination ratios. Our approach performs a dynamic analysis of the cosine similarity between each data point and its reconstruction during the early training stages of an auto-encoder, mapping points into a dynamic space where anomalous regions naturally exhibit lower density. By executing ``hard cleaning''\textemdash removing all identified anomalous candidates from the training pool\textemdash we systematically improve data quality. Because this cleaning occurs at the data level, the security and reliability improvements generalize seamlessly across various downstream anomaly detection architectures. Evaluating our framework across 8 distinct models and 10 security-relevant datasets, our approach achieves up to 100\% contamination reduction, yielding average improvements of 11.2\% in F1 score and 7.3\% in classification accuracy.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：异常检测、Autoencoder、数据清洗、AI安全，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Jordan F. Masakuna, Ahmed Yacine, Djeff K. Nkashama, Arian Soltani, Marc Frappier, Pierre M. Tardif, Froduald Kabanza），经 AITOP 多维评分管线结构化提炼。