Leon Derczynski

Leon Derczynski is principal research scientist in LLM security at NVIDIA and professor of natural language processing (NLP) at ITU Copenhagen. He has published over 100 NLP papers. Leon contributes to leading bodies on LLM security, is on the OWASP LLM Top 10 core team, works on ML Commons, and is the founder of the ACL SIG on NLP Security. Leon heads up the LLM vulnerability scanner garak with the NVIDIA NeMo Guardrails team.
Avatar photo

Posts by Leon Derczynski

A cybersecurity image.
Trustworthy AI / Cybersecurity Oct 02, 2025

Practical LLM Security Advice from the NVIDIA AI Red Team

Over the last several years, the NVIDIA AI Red Team (AIRT) has evaluated numerous and diverse AI-enabled systems for potential vulnerabilities and security... 8 MIN READ
Decorative image.
Trustworthy AI / Cybersecurity Feb 25, 2025

Defining LLM Red Teaming

There is an activity where people provide inputs to generative AI technologies, such as large language models (LLMs), to see if the outputs can be made to... 10 MIN READ
Trustworthy AI / Cybersecurity Sep 18, 2024

NVIDIA Presents AI Security Expertise at Leading Cybersecurity Conferences

Each August, tens of thousands of security professionals attend the cutting-edge security conferences Black Hat USA and DEF CON. This year, NVIDIA AI security... 9 MIN READ