Summary
Decentralized autonomous organizations (DAOs) make decisions using proposals described in natural language that, if passed, execute computer code. Sometimes, the description and the actual code do different things, tricking voters into approving harmful actions, called Description-Execution Mismatch (DEMI) attacks. The authors built a system that watches how each DAO usually behaves and simulates proposals’ real outcomes, then uses language models to check if each code action is clearly explained in the proposal. Their method catches most problematic proposals accurately and works well across many DAOs and language models, even against people trying to fool the system.
What this means in practice
- •For dao platform operators: Detect deceptive proposals that mismatch descriptions and executed code before votes finalize to protect DAO assets and governance.
- •For blockchain security teams: Simulate proposal lifecycles and verify textual justifications of code actions to identify and prevent fraudulent governance attacks.
Authors
Bowen Cai, Nanzi Yang, Weiheng Bai, Youshui Lu, Yajin Zhou, Kangjie Lu
Abstract
Decentralized autonomous organizations (DAOs) change protocols through a proposal-based process: initiators submit a proposal, members vote on it based on its natural-language description, and if it passes, the project executes the code behind it. This process is inherently vulnerable to deceptive proposals, where the described intent and the actual code execution mismatch. A malicious proposer can submit a benign-looking description to pass voting while the executed code transfers funds or seizes control of the protocol, which we call a Description-Execution Mismatch (DEMI) attack. We present the first systematic framework for DEMI detection in real DAO governance. First, the diversity of DAO deployments makes a unified, scalable analysis difficult; we address this with a DAO-agnostic simulation framework that builds a per-DAO governance profile from historical on-chain transactions and then drives each new proposal through the full governance lifecycle to obtain its execution behavior. Second, free-form descriptions and structured execution traces are hard to compare; we address this with an evidence-mapping paradigm that requires an LLM to locate explicit per-action textual justifications rather than issue a holistic judgment, substantially improving precision and recall over direct querying. On a large-scale dataset of real-world Ethereum DAO governance, our simulation derives execution results for 92.7% of active DAOs and 89.3% of executed proposals, far exceeding existing platforms. Our detector reaches 81.7% mean precision and 98.3% mean recall under stratified cross-validation, and evidence mapping generalizes across LLM vendors rather than depending on one model. Under a systematic red-team/blue-team evaluation, the Robustness Guard defends most adaptive attacks even against an adversary that knows the detector, and this robustness generalizes to held-out proposals.