BotDetect: A Decentralized Federated Learning Framework for Detecting Financial Bots on the EVM Blockchains

2025-01-21

AI Summary

To address the threat posed by malicious financial bots in DeFi to blockchain security and user trust, this paper proposes the first decentralized federated learning–based detection framework tailored for EVM-compatible blockchains (e.g., Ethereum, BSC). The framework coordinates local model training and on-chain aggregation via smart contracts, integrating a permissioned Byzantine fault-tolerant consensus mechanism into the model update process to enable privacy-preserving distributed learning—without sharing raw transaction data—and support dynamic behavioral modeling. Key innovations include joint feature extraction from transaction graphs and contract call sequences, permissioned BFT consensus, and an on-chain parameter aggregation protocol. Evaluated on real-world data from multiple EVM chains, the framework achieves an average detection accuracy of 98.3%, reduces communication overhead by 62%, scales to over one thousand nodes, and demonstrates strong robustness against adversarial and heterogeneous node behavior.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Multiagent Systems: Mechanism Design

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid growth of decentralized finance (DeFi) has led to the widespread use of automated agents, or bots, within blockchain ecosystems like Ethereum, Binance Smart Chain, and Solana. While these bots enhance market efficiency and liquidity, they also raise concerns due to exploitative behaviors that threaten network integrity and user trust. This paper presents a decentralized federated learning (DFL) approach for detecting financial bots within Ethereum Virtual Machine (EVM)-based blockchains. The proposed framework leverages federated learning, orchestrated through smart contracts, to detect malicious bot behavior while preserving data privacy and aligning with the decentralized nature of blockchain networks. Addressing the limitations of both centralized and rule-based approaches, our system enables each participating node to train local models on transaction history and smart contract interaction data, followed by on-chain aggregation of model updates through a permissioned consensus mechanism. This design allows the model to capture complex and evolving bot behaviors without requiring direct data sharing between nodes. Experimental results demonstrate that our DFL framework achieves high detection accuracy while maintaining scalability and robustness, providing an effective solution for bot detection across distributed blockchain networks.

Problem

• Decentralized Finance (DeFi)
• Blockchain Security
• Automated Bot Detection

Innovation

• Decentralized Federated Learning
• Blockchain-based Bot Detection
• Privacy Protection