# New Online Communities: Graph Deep Learning on Anonymous Voting Networks to Identify Sybils in Polycentric Governance

arXiv: https://arxiv.org/abs/2311.17929 · HTML: https://mlsanity.com/paper/2311.17929/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 83 references that are in the map.
- First posted on arXiv 25 Nov 2023.

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

- [Detecting Mixing Services via Mining Bitcoin Transaction Network with Hybrid Motifs](https://mlsanity.com/paper/2001.05233/) (2020)
- [Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity](https://mlsanity.com/paper/2005.14635/) (2020)
- [Behavior-aware Account De-anonymization on Ethereum Interaction Graph](https://mlsanity.com/paper/2203.09360/) (2022)
- [BitcoinHeist: Topological Data Analysis for Ransomware Detection on the Bitcoin Blockchain](https://mlsanity.com/paper/1906.07852/) (2019)
- [Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods](https://mlsanity.com/paper/1611.03941/) (2016)
- [Ransomware Payments in the Bitcoin Ecosystem](https://mlsanity.com/paper/1804.04080/) (2018)
- [How to Peel a Million: Validating and Expanding Bitcoin Clusters](https://mlsanity.com/paper/2205.13882/) (2022)
- [Blockchain Technology as a Regulatory Technology: From Code is Law to Law is Code](https://mlsanity.com/paper/1801.02507/) (2018)
- [Auto.gov: Learning-based Governance for Decentralized Finance (DeFi)](https://mlsanity.com/paper/2302.09551/) (2023)
- [Unpacking How Decentralized Autonomous Organizations (DAOs) Work in Practice](https://mlsanity.com/paper/2304.09822/) (2023)
- [Resurrecting Address Clustering in Bitcoin](https://mlsanity.com/paper/2107.05749/) (2021)
- [An Empirical Study on Snapshot DAOs](https://mlsanity.com/paper/2211.15993/) (2022)
- [Decentralization illusion in Decentralized Finance: Evidence from tokenized voting in MakerDAO polls](https://mlsanity.com/paper/2203.16612/) (2022)
- [Cooperation among an anonymous group protected Bitcoin during failures of decentralization](https://mlsanity.com/paper/2206.02871/) (2022)
- [Altruistic and Profit-oriented: Making Sense of Roles in Web3 Community from Airdrop Perspective](https://mlsanity.com/paper/2303.08457/) (2023)

## Built on by (most cited first, 1 of 1)

- [DAO-enabled decentralized physical AI: A new paradigm for human-machine collaboration](https://mlsanity.com/paper/2605.04522/) (2026)

## Abstract (arXiv)

This research examines the polycentric governance of digital assets in blockchain-based Decentralized Autonomous Organizations (DAOs). It offers a theoretical framework and addresses a critical challenge facing decentralized governance by developing a method to identify Sybils, or spurious identities. Sybils pose significant organizational sustainability threats to DAOs and other, commons-based online communities, and threat models are identified. The experimental method uses an autoencoder architecture and graph deep learning techniques to identify Sybil activity in a DAO governance dataset (snapshot.org). Specifically, a Graph Convolutional Neural Network (GCNN) learned voting behaviours and a fast vector clustering algorithm used high-dimensional embeddings to identify similar nodes in a graph. The results reveal that deep learning can effectively identify Sybils, reducing the voting graph by 2-5%. This research underscores the importance of Sybil resistance in DAOs, identifies challenges and opportunities for forensics and analysis of anonymous networks, and offers a novel perspective on decentralized governance, informing future policy, regulation, and governance practices.