Nanna InieLeon DerczynskiComputer Science DepartmentResearchartificial intelligence
What are the intentions and profile of someone trying to use LLMs for malicious purposes? And how do they do it? In a new study, researchers from ITU define so-called “red teaming” of LLMs to enable better security in the future.
This page is printed from https://prod.93.itu.dk/Om-ITU/Presse/ITU-i-medierne/2019?page=-110999