English | 中文README

AC-MIL

Introduction

This repository provides the official implementation of Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms, a multiple instance learning framework for liveroom fraud detection.

Our work has been accepted by KDD’ 2026.

Quick Start

Run the following script to launch a quick training and evaluation workflow:

bash .trail_training/run.sh

Citation

If you find this work useful, please kindly cite it as follows:

@article{qiao2026live,
  title={Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms},
  author={Qiao, Yiran and Chen, Jing and Ao, Xiang and Zhong, Qiwei and Liu, Yang and He, Qing},
  journal={arXiv preprint arXiv:2602.03520},
  year={2026}
}

Security

If you discover a potential security issue in this project, or think you may have discovered a security issue, we ask that you notify Bytedance Security via our security center or vulnerability reporting email.

Please do not create a public GitHub issue.

License

This project is licensed under the MIT License.