As enterprises rush to deploy copilots and autonomous agents, security teams are discovering that testing AI systems requires ...

Members of a Microsoft Corp. team tasked with using hacker tactics to find cybersecurity issues have open-sourced an internal tool, PyRIT, that can help developers find risks in their artificial ...

Microsoft has open sourced a key piece of its AI security, offering a toolkit that links data sets to targets and scores results, in the cloud or with small language models. At the heart of ...

Many risk-averse IT leaders view Microsoft 365 Copilot as a double-edged sword. CISOs and CIOs see enterprise GenAI as a powerful productivity tool. After all, its summarization, creation and coding ...

A surge in real-world attacks against agentic AI systems is reshaping how we think about risk. Based on 12 months of red ...

As concerns mount about AI’s risk to society, a human-first approach has emerged as an important way to keep AIs in check. That approach, called red-teaming, relies on teams of people to poke and prod ...

The group responsible for red teaming of over 100 generative AI products at Microsoft has concluded that the work of building safe and secure AI systems will never be complete. In a paper published ...

Ram Shankar Siva Kumar reflects on his time on Microsoft's AI Red Team, a group of technical experts who emulate real-world cyberattacks to allow companies to strengthen their technologies. "AI red ...