Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Ahmed Mounsf Rafik Bendada, Abdelaziz Amara Korba, Mouhamed Amine Bouchiha, Yacine Ghamri-Doudane

TL;DR

This paper presents a decentralized federated learning (DFL) approach for detecting financial bots within Ethereum Virtual Machine (EVM)-based blockchains, and demonstrates that the DFL framework achieves high detection accuracy while maintaining scalability and robustness, providing an effective solution for bot detection across distributed blockchain networks.

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.

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

TL;DR

This paper presents a decentralized federated learning (DFL) approach for detecting financial bots within Ethereum Virtual Machine (EVM)-based blockchains, and demonstrates that the DFL framework achieves high detection accuracy while maintaining scalability and robustness, providing an effective solution for bot detection across distributed blockchain networks.

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.
Paper Structure (10 sections, 9 equations, 4 figures, 4 tables, 1 algorithm)

This paper contains 10 sections, 9 equations, 4 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Proposed Solution
  4. System Model
  5. Decentralized Federated Training
  6. EXPERIMENTS AND RESULTS ANALYSIS
  7. Data Preprocessing
  8. Detection Performance Evaluation
  9. Blockchain Performance Evaluation
  10. Conclusion

Figures (4)

  • Figure 1: Workflow of the proposed framework: Step-1. get initial global model; Step-2. local training; Step-3. submit update; Step-4. aggregation; Step-5. write global model and repeat.
  • Figure 2: Heatmap of Accuracy and Loss Over Rounds for the multiclassifier model with 3 training clients
  • Figure 3: Confusion Matrices: DFL (4 and 5 clients) vs. centralized learning
  • Figure 4: Latency and Throughput comparison under two workload types and two block times