The group responsible for red teaming of over 100 generative AI products at Microsoft has concluded that the work of building ...

Affiliate Ram Shankar Siva Kumar and coauthors suggest ways that Microsoft and other tech giants can mitigate the security risks inherent in emerging AI technologies.

Scientists have warned that artificial intelligence (AI) has crossed a "red line," as the technology now has the ability to ...

AI crosses ‘red line’ after learning to replicate itself - ‘Successful self-replication is the essential step for AI to ...

While automation is a valuable tool for scaling red teaming efforts, it cannot replace human judgment and creativity. Subject ...

Scientists say AI has crossed a critical 'red line' after demonstrating how two popular large language models could clone ...

Read about DARPA’s requirements for new tech to evaluate the vulnerability of artificial intelligence-enabled systems.

According to a recent security report, rising AI star DeepSeek R1 already some security flaws out of the gate.

As the industry evolves, proactive measures will be key to ensuring the responsible development and deployment of advanced ...

The agency identifies four key areas of interest: AI red teaming frameworks Cyber methods for affecting AI systems Electronic warfare techniques Physical manufacturing of adversarial effects ...