> For the complete documentation index, see [llms.txt](https://docs.salusec.io/untitled/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.salusec.io/untitled/lightning-cat/machine-learning.md).

# 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="/files/AFv4hyfiu8762IY0rPp2" alt=""><figcaption></figcaption></figure>