other8.0 / 10
Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
Abstract
Shows realistic challenges for cyber offense can be completed by SoTA LLMs while open source models lag behind.
Research area
robustness to domain shifts
Published
—
Source
other
Org
Apart Research
Sign in to read and join the discussion.