AI & ML Practical Magic

AI agents are finding multi-million dollar holes in bank code that even the best human experts completely walked past.

March 30, 2026

Original Paper

Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

Ziqiao Kong, Wanxu Xia, Chong Wang, Yi Lu, Pan Li, Shaohua Li, Zong Cao, Yang Liu

arXiv · 2603.26270

The Takeaway

Smart contracts govern billions in digital finance but are notoriously difficult to audit for bugs. This AI system 'studied' years of human audit reports to uncover dozens of previously unknown high-severity vulnerabilities in real-world projects, significantly outperforming existing automated tools.

From the 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