4 papers
Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
Raja Sekhar Rao Dheekonda, Will Pearce, Nick Landers
AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current app…
AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
Ads Dawson, Rob Mulla, Nick Landers +1
We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning (AI/ML…
The Automation Advantage in AI Red Teaming
Rob Mulla, Ads Dawson, Vincent Abruzzon +4
This paper analyzes Large Language Model (LLM) security vulnerabilities based on data from Crucible, encompassing 214,271 attack attempts by 1,674 users across 30 LLM challenges. O…
Machine Learning for Offensive Security: Sandbox Classification Using Decision Trees and Artificial Neural Networks
Will Pearce, Nick Landers, Nancy Fulda
The merits of machine learning in information security have primarily focused on bolstering defenses. However, machine learning (ML) techniques are not reserved for organizations w…