Joseph Lucas

Joe is a Principal Offensive Security Researcher focused on AI at NVIDIA. He is the founder and Chair of the NumFOCUS Security Committee and is a member of the Jupyter Security Council. He was one of the architects and hosts of the DEF CON 30 AI Village Capture the Flag competition and is passionate about machine learning security education. He served in the US Army at US Cyber Command and the 101st Airborne Division. He holds a master's degree in Computer Science from Georgia Institute of Technology and a bachelor's degree in Mathematics from the United States Military Academy.
Joseph Lucas

Posts by Joseph Lucas

A cybersecurity image.
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
Cybersecurity Sep 26, 2025

Why CVEs Belong in Frameworks and Apps, Not AI Models

The Common Vulnerabilities and Exposures (CVE) system is the global standard for cataloging security flaws in software. Maintained by MITRE and backed by CISA,... 7 MIN READ
Cybersecurity Apr 29, 2025

Structuring Applications to Secure the KV Cache

When interacting with transformer-based models like large language models (LLMs) and vision-language models (VLMs), the structure of the input shapes the... 11 MIN READ
Cybersecurity Dec 16, 2024

Sandboxing Agentic AI Workflows with WebAssembly

Agentic AI workflows often involve the execution of large language model (LLM)-generated code to perform tasks like creating data visualizations. However, this... 7 MIN READ
An illustration showing a securit alert.
Cybersecurity Jul 11, 2024

Defending AI Model Files from Unauthorized Access with Canaries

As AI models grow in capability and cost of creation, and hold more sensitive or proprietary data, securing them at rest is increasingly important.... 6 MIN READ
Data Science Jun 27, 2024

Secure LLM Tokenizers to Maintain Application Integrity

This post is part of the NVIDIA AI Red Team’s continuing vulnerability and technique research. Use the concepts presented to responsibly assess and increase... 6 MIN READ