# Machine Learning

Salus Lightning Cat employs machine learning techniques for smart contract vulnerability detection. **We have trained three deep learning models for detecting vulnerabilities in smart contracts: Optimized-CodeBERT, Optimized-LSTM, and Optimized-CNN.** To accurately extract vulnerability features, we obtain code snippets from vulnerable functions, preserving key vulnerability characteristics. By leveraging the CodeBERT pre-trained model for data preprocessing, we can more accurately capture the syntax and semantics of the code, thereby **improving the performance of vulnerability detection.**

<figure><img src="https://1958959434-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FFQPoyXrMUD1C4DzLY5ER%2Fuploads%2F0IjMxVATZqzOK3tA2t1f%2Fmachin%20learning.png?alt=media&#x26;token=730ec299-9e78-43c4-81c3-343e918eb912" alt=""><figcaption></figcaption></figure>