Microsoft’s own baddie team ‘attacked’ more than 100 generative AI products: Here’s what they learnt

• Microsoft created an AI red team back in 2018 as it foresaw the rise of AI
• A red team represents the enemy; and adopts the adversarial persona.
• Latest whitepaper from the team hopes to address common vulnerabilities in AI systems and LLMs

Over the past seven years, Microsoft has been addressing the risks in artificial intelligence systems through its dedicated AI ‘red team’.

Established to foresee and counter the growing challenges posed by advanced AI systems, this team adopts the role of threat actors, ultimately aiming to identify vulnerabilities before they can be exploited in the real world.