Led by Toufik Ahmed, University Professor at Bordeaux and researcher at LaBRI, in collaboration with Knocknock and ADACIS, with technical support from CATIE (as subcontractor), PENTEST.LLM is funded by the French government as part of France 2030 and the development of innovative critical cybersecurity technologies. The project is part of a 100% regional dynamic in the Nouvelle-Aquitaine region.
This project leverages the power of generative AI and large language models (LLMs) to protect our digital infrastructures. These emerging technologies are transforming the industry by offering new solutions to the increasingly complex threats of today's digital landscape.
The aim of PENTEST.LLM is to specialize an LLM by fine-tuning then testing, validating and deploying it, specifically designed for cybersecurity. This model aims to increase the ability of slotters to detect and exploit new vulnerabilities through the automatic generation of exploit scripts (payloads), based on information gathered manually during testing, as well as on open sources such as OSINT, CVEs, and many others.
.