Project Name: Automatic TRON Address Clustering
Project Track: Web3
Team Name: MistTrack Team
Team Member(s): 3
DevPost URL: MistTrack: Automatic TRON Address Clustering | Devpost
Project Goal: Our goal this time is to present an advanced system utilizing machine learning and graph computing to analyze attributes of TRON addresses to identify common user addresses, hot wallet addresses, and cold wallet addresses in the TRON ecosystem. At the same time, our analysis will examine each address’s characteristics and relationships to aid in the tracking of hacker addresses and activity, allowing relevant personnel to access additional insight into a wallet.
In this age of information boom, the SlowMist security team discovered that malicious actors frequently utilize social media, phishing websites, and other methods to steal users’ digital assets. Our address identification mechanism primarily uses graph and machine learning algorithms to evaluate the public transaction history of TRON’s users and label their addresses into 3 separate categories: Hot wallet, Cold wallet, and Common users.
Support Token include: USDT (Contract Address: TR7NHqjeKQxGTCi8q8ZY4pL8otSzgjLj6t), USDC(Contract Address: TEkxiTehnzSmSe2XqrBj4w32RUN966rdz8) and other TRC20 tokens.
This is accomplished by combining the graph algorithm with node mining techniques to execute large-scale mining of transaction attributes of user address transactions. This also has the ability to perform influence analysis, community discovery based on tag propagation algorithm, and transaction path discovery based on graph traversal algorithm.
- GitHub - slowmist/automatic-tron-address-clustering: We use machine learning and graph algorithms to analyze the attributes of TRON addresses with the goal of assisting in the tracking of illicit funds.
- MistTrack - A Crypto Tracking and Compliance Platform for Everyone
Project Test Instructions:
- Install automatic-tron-address-clustering/install.md at main · slowmist/automatic-tron-address-clustering · GitHub
- Running automatic-tron-address-clustering/code.md at main · slowmist/automatic-tron-address-clustering · GitHub
- Machine Learning (finished)
- Graph Algorithms (finished)
- Improve the algorithm to enhance recognition accuracy
- Access additional TRON ecosystem functionality, expand data scope, and enhance processing efficacy
Since this hackathon is an ongoing funding program, projects that have great potential and good community engagement are likely to win and receive additional funding after the initial hackathon. Therefore, participants should update their project posts to be as detailed as possible and answer any community questions during the hackathon period.