[2603.26270] Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

Computer Science > Cryptography and Security arXiv:2603.26270 (cs) [Submitted on 27 Mar 2026] Title:Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization Authors:Ziqiao Kong, Wanxu Xia, Chong Wang, Yi Lu, Pan Li, Shaohua Li, Zong Cao, Yang Liu View a PDF of the paper titled Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization, by Ziqiao Kong and 7 other authors View PDF HTML (experimental) Abstract:Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic. We observe that recurring vulnerabilities across diverse DeFi business models often share the same underlying economic mechanisms, which we term DeFi semantics, and that capturing these shared abstractions can enable more systematic auditing. Building on this insight, we propose Knowdit, a knowledge-driven, agentic framework for smart contract vulnerability detection. Knowdit first constructs an auditing knowledge graph from historical human audit reports, linking fine-grained DeFi semantics with recurring vulnerability patterns. Given a new project, a multi-agent framework leverages this knowledge through an iterative loop of specification generation, harness synthesis, fuzz execution, and finding reflection, driven by a shared working memory for continuous refinement. We evaluate ...