Bytewhisper Security is excited to announce that, in partnership with the Linux Foundation’s Alpha-Omega project, we will be releasing a series of guides and discussions aimed at helping users safely and effectively utilize open source Generative AI tooling.
Alpha-Omega is an associated project of the OpenSSF, established in February 2022, funded by Microsoft, Google, and Amazon, with a mission to protect society by catalyzing sustainable security improvements to the most critical open source software projects and ecosystems. The project aims to build a world where critical open source projects are secure and where security vulnerabilities are found and fixed quickly.
In each article we’ll aim to help explain core security concerns with both Large Language Models (LLMs) and the open source tooling, as well as guidance for reducing risk from those concerns. For our first topic, we’d like to take a look at Prompt Injection. In the following article, we discuss building an application with a local LLM (using Ollama) and adding additional controls to reduce risk from Prompt Injection.
If you have questions, comments, or requests for future discussion topics, don’t hesitate to reach out to us at contact@bytewhispersecurity.com
