Back to updates

AI Security - 1

2026 (9)

August (1)

security: Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps

Microsoft Security Blog

2026-08-04

Microsoft says it is expanding its Zero Trust for AI strategy with new tools and guidance aimed at securing AI agents and DevSecOps environments. The post highlights a broader security approach for AI and related development workflows.

July (4)

security: ​​​​What’s new in Microsoft Security: July 2026

Microsoft Security Blog

2026-07-30

Microsoft’s July 2026 Security update highlights new capabilities for securing AI environments, using AI for defense, and improving the underlying systems that AI-powered operations rely on. The provided excerpt does not include specific product changes or feature details.

security: Enhancing AI security through global AI red teaming

Microsoft Security Blog

2026-07-27

Microsoft announced EXTRA, a global AI security initiative focused on AI safety research and red teaming. The program partners with universities, researchers, and regional experts to identify emerging AI risks and improve testing of frontier AI systems.

security: Microsoft at Black Hat USA 2026: Defending trust in the age of AI and supply chain attacks

Microsoft Security Blog

2026-07-17

Microsoft Security says it will be at Black Hat USA 2026 with sessions on supply chain research, hands-on security experiences, expert conversations, and a reception. The post frames the event around trust, AI, and supply chain attacks.

github: CodeQL 2.26.0 adds Kotlin 2.4.0 support and AI prompt injection detection

GitHub

2026-07-10

CodeQL 2.26.0 adds support for Kotlin 2.4.0 and introduces detection for AI prompt injection issues in code scanning. The release updates the static analysis engine used by GitHub code scanning.

June (4)

security: Securing AI agents: When AI tools move from reading to acting

Microsoft Security Blog

2026-06-30

The post explains MCP tool poisoning as an attack that can turn trusted AI agents into a control plane for data loss. It describes how attackers manipulate tool descriptions to induce unauthorized actions, and outlines detection, containment, and prevention approaches.

security: Guarding AI memory

Microsoft Security Blog

2026-06-22

Microsoft Security Blog discusses risks to AI memory and outlines defenses against attacks that target what an AI system remembers. The post is a high-level security overview rather than a product release note.

security: New Forrester study shows customers who unified with Microsoft Security benefited from 124% ROI

Microsoft Security Blog

2026-06-18

Microsoft cites a new Forrester Total Economic Impact study saying organizations that consolidated on Microsoft Security saw a 124% ROI, lower risk, and improved readiness to secure AI. The post is a summary announcement and does not include detailed methodology or product changes.

security: Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

Microsoft Security Blog

2026-06-04

Microsoft Security Blog says a year of red teaming agentic AI systems led to an updated failure-mode taxonomy. The update adds seven new failure modes, including supply chain compromise and goal hijacking, along with recommended mitigations.