ContractLens finds hidden smart contract security signals in AI models
ContractLens: Latent Security Knowledge for Malicious Smart Contract Detection
Cryptography and Security
Summary
Detecting harmful smart contracts is important to keep digital blockchain spaces safe. The authors present ContractLens, which finds hidden clues inside large AI language models to tell bad contracts from good ones. It picks out key parts of the AI’s 'brain' to better detect scams without changing the AI model itself. This method works well across different models and can still spot new kinds of scams with little extra training.
What this means in practice
- •For blockchain security teams: Enhance smart contract auditing by using contract-specific signals identified within pretrained AI models for better detection of malicious contracts.
- •For cybersecurity operations centers: Use compact AI-derived features to detect new or unseen malicious smart contract behaviors with limited labeled samples.
Authors
Shuyi Miao, Xinyi Huang, Wangjie Qiu, Fei Shen, Jinchun He, Zhiming Zheng, Tat-Seng Chua
Abstract
Detecting malicious smart contracts is essential to safeguarding the Web3.0 ecosystem. However, existing auditing methods based on large language models (LLMs) largely rely on prompt engineering or attack-specific fine-tuning, while the internal representations that support malicious logic detection remain poorly characterized. To address this gap, we propose ContractLens, a framework that localizes and uses latent security knowledge in pretrained LLMs for interpretable malicious smart contract detection. Specifically, we first use layerwise linear probes to identify candidate layers that distinguish malicious from benign contracts, then select critical layers based on their sensitivity to malicious logic removal and stability under behaviour-preserving surface modifications. Next, within these critical layers, we combine activation contrast, malicious-logic specificity, and probe weights into a tri-factor importance score and adaptively select malicious contract-discriminative units (MCDUs) using the knee point of the ranked score curve. Finally, we concatenate the selected units' activations into a compact representation and train a lightweight classifier for detection, keeping the pretrained model frozen throughout. Neuron masking experiments show that masking MCDUs causes larger drops in detection performance than masking randomly selected neurons or neurons matched in activation magnitude. ContractLens achieves higher average detection accuracy than the evaluated methods on all three pretrained models. Further evaluations demonstrate generalization to unseen malicious intents and show that, with the identified MCDUs fixed, a classifier trained on few labelled samples can still achieve strong detection performance.