AI RESEARCH
Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
arXiv CS.AI
•
ArXi:2605.04019v1 Announce Type: new 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 approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows - assembling attacks, transforms, and scorers. When results fall short, workflows must be rebuilt. As a result, operators spend time constructing workflows than probing targets for security and safety vulnerabilities. We make three contributions: 1. Agentic interface.