English

RMSL: Weakly-Supervised Insider Threat Detection with Robust Multi-sphere Learning

Cryptography and Security 2025-08-18 v1 Artificial Intelligence Machine Learning

Abstract

Insider threat detection aims to identify malicious user behavior by analyzing logs that record user interactions. Due to the lack of fine-grained behavior-level annotations, detecting specific behavior-level anomalies within user behavior sequences is challenging. Unsupervised methods face high false positive rates and miss rates due to the inherent ambiguity between normal and anomalous behaviors. In this work, we instead introduce weak labels of behavior sequences, which have lower annotation costs, i.e., the training labels (anomalous or normal) are at sequence-level instead of behavior-level, to enhance the detection capability for behavior-level anomalies by learning discriminative features. To achieve this, we propose a novel framework called Robust Multi-sphere Learning (RMSL). RMSL uses multiple hyper-spheres to represent the normal patterns of behaviors. Initially, a one-class classifier is constructed as a good anomaly-supervision-free starting point. Building on this, using multiple instance learning and adaptive behavior-level self-training debiasing based on model prediction confidence, the framework further refines hyper-spheres and feature representations using weak sequence-level labels. This approach enhances the model's ability to distinguish between normal and anomalous behaviors. Extensive experiments demonstrate that RMSL significantly improves the performance of behavior-level insider threat detection.

Keywords

Cite

@article{arxiv.2508.11472,
  title  = {RMSL: Weakly-Supervised Insider Threat Detection with Robust Multi-sphere Learning},
  author = {Yang Wang and Yaxin Zhao and Xinyu Jiao and Sihan Xu and Xiangrui Cai and Ying Zhang and Xiaojie Yuan},
  journal= {arXiv preprint arXiv:2508.11472},
  year   = {2025}
}

Comments

15 pages

R2 v1 2026-07-01T04:51:53.842Z