eSentire Debuts Customizable Framework to Govern, Monitor Large Language Models

eSentire, a Top 40 MDR, has debuted an open-source implementation framework to help security teams improve how they govern and monitor the use of Large Language Models (LLMs) internally.

The company first developed its LLM Gateway for internal use of ChatGPT, Google Bard and other LLMs, officials said. Over time, it customized the Gateway with additional controls and business policies specific to eSentire. The developer subsequently figured the LLM Gateway could be applied as a reference implementation for IT administrators to access as they evaluate future full-scale gateway solutions.

Alexander Feick, eSentire Labs vice president, explained how generative artificial intelligence (AI) is “democratizing” innovation:

"Having the right controls is imperative to tap into its power, securely. We are helping security practitioners take the first step to gaining visibility and control over this exciting innovation with the eSentire LLM Gateway."

The LLM Gateway is available now for download on GitHub.

A Protective Security Layer and More

Benefits of the eSentire LLM Gateway include: (per eSentire)

Creates a protective layer between corporate data and open AI applications including ChatGPT.

All LLM interactions are logged, enhancing monitoring & security control, while also surfacing core use cases from functional and power users.

As an open-source framework, security practitioners can integrate and apply their own security controls including corporate policies, usage rules and prompts, and contribute suggestions to further collaboration with the broader cybersecurity community.

Basic recommendations on how to visualize and track LLM usage are included within the eSentire LLM Gateway’s initial plug-ins.