# Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms

arXiv: https://arxiv.org/abs/2602.03520 · HTML: https://mlsanity.com/paper/2602.03520/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology](https://mlsanity.com/paper/2206.01794/) (2022)
- [Graph Neural Networks for Financial Fraud Detection: A Review](https://mlsanity.com/paper/2411.05815/) (2024)
- [VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform](https://mlsanity.com/paper/2504.14904/) (2025)
- [Interleaved Sequence RNNs for Fraud Detection](https://mlsanity.com/paper/2002.05988/) (2020)
- [Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection](https://mlsanity.com/paper/2201.01004/) (2022)
- [Measuring and Characterizing Hate Speech on News Websites](https://mlsanity.com/paper/2005.07926/) (2020)
- [Detecting Rumours with Latency Guarantees using Massive Streaming Data](https://mlsanity.com/paper/2205.06580/) (2022)
- [VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection](https://mlsanity.com/paper/2408.00513/) (2024)

## Built on by (most cited first, 2 of 2)

- [Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessment](https://mlsanity.com/paper/2606.02946/) (2026)
- [LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems](https://mlsanity.com/paper/2608.26849/) (2026)

## Abstract (arXiv)

Live streaming has become a cornerstone of today's internet, enabling massive real-time social interactions. However, it faces severe risks arising from sparse, coordinated malicious behaviors among multiple participants, which are often concealed within normal activities and challenging to detect timely and accurately. In this work, we provide a pioneering study on risk assessment in live streaming rooms, characterized by weak supervision where only room-level labels are available. We formulate the task as a Multiple Instance Learning (MIL) problem, treating each room as a bag and defining structured user-timeslot capsules as instances. These capsules represent subsequences of user actions within specific time windows, encapsulating localized behavioral patterns. Based on this formulation, we propose AC-MIL, an Action-aware Capsule MIL framework that models both individual behaviors and group-level coordination patterns. AC-MIL captures multi-granular semantics and behavioral cues through a serial and parallel architecture that jointly encodes temporal dynamics and cross-user dependencies. These signals are integrated for robust room-level risk prediction, while also offering interpretable evidence at the behavior segment level. Extensive experiments on large-scale industrial datasets from Douyin demonstrate that AC-MIL significantly outperforms MIL and sequential baselines, establishing new state-of-the-art performance in room-level risk assessment for live streaming. Moreover, AC-MIL provides capsule-level interpretability, enabling identification of risky behavior segments as actionable evidence for intervention. The project page is available at: https://qiaoyran.github.io/AC-MIL/.