SoK: Security and Privacy of AI Agents for Blockchain

2025-09-08

AI Summary

A systematic survey of security and privacy challenges at the intersection of blockchain and AI agents remains absent. Method: This paper establishes the first structured knowledge framework for blockchain-based AI agents, rigorously defining threat models, attack surfaces, and defense mechanisms. Through a systematic literature review—augmented by on-chain data analysis, smart contract auditing, and AI behavioral modeling—it classifies and evaluates AI agent applications across transaction strategy optimization, on-chain analytics, and vulnerability detection. Contribution/Results: The study uncovers critical risks, technical limitations, and implicit assumptions in current practice, identifying core challenges including insufficient verifiability, on-chain data noise, and incentive misalignment. It further proposes key directions for developing trustworthy AI agents. This work provides the first structured analytical framework to advance both theoretical understanding and practical deployment in this emerging domain.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Blockchain and smart contracts have garnered significant interest in recent years as the foundation of a decentralized, trustless digital ecosystem, thereby eliminating the need for traditional centralized authorities. Despite their central role in powering Web3, their complexity still presents significant barriers for non-expert users. To bridge this gap, Artificial Intelligence (AI)-based agents have emerged as valuable tools for interacting with blockchain environments, supporting a range of tasks, from analyzing on-chain data and optimizing transaction strategies to detecting vulnerabilities within smart contracts. While interest in applying AI to blockchain is growing, the literature still lacks a comprehensive survey that focuses specifically on the intersection with AI agents. Most of the related work only provides general considerations, without focusing on any specific domain. This paper addresses this gap by presenting the first Systematization of Knowledge dedicated to AI-driven systems for blockchain, with a special focus on their security and privacy dimensions, shedding light on their applications, limitations, and future research directions.

Problem

• Lack of comprehensive survey on AI agents for blockchain
• Focusing on security and privacy of AI-driven blockchain systems
• Addressing applications, limitations, and future research directions

Innovation

• AI agents for blockchain interaction
• Focus on security and privacy
• Systematization of Knowledge approach