At its core, they stated, “AI pink teaming strives to push past model-level security benchmarks by emulating real-world assaults towards end-to-end techniques. Nonetheless, there are various open questions on how pink teaming operations ought to be performed and a wholesome dose of skepticism concerning the efficacy of present AI pink teaming efforts.”
The paper famous that, when it was shaped in 2018, the Microsoft AI Crimson Workforce (AIRT) centered totally on figuring out conventional safety vulnerabilities and evasion assaults towards classical ML fashions. “Since then,” it stated, “each the scope and scale of AI pink teaming at Microsoft have expanded considerably in response to 2 main traits.”
The primary, it stated, is that AI has turn into extra refined, and the second is that Microsoft’s latest investments in AI have resulted within the improvement of many extra merchandise that require pink teaming. “This improve in quantity and the expanded scope of AI pink teaming have rendered totally handbook testing impractical, forcing us to scale up our operations with the assistance of automation,” the authors wrote.
