In 2024 we looked at the possibility of leveraging open weights LLMs for source code analysis. The answer was clearly negative, as a small code base could easily take 200K tokens, more than any context window offered by open weights models. The table below summarizes the top LLMs by context window as of today. Context […]
Compass Security Blog
Offensive Defense
Given the explosion of development and interest in deep learning models in the past year, we decided to research on the topic to increase our know-how and find applications where these technologies can be leveraged in offensive security engagements.
This posts explores the use of machine learning for voice cloning and how it can be used for social engineering.
© 2025 Compass Security Blog