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