Microsoft supports Coordinated Vulnerability Disclosure (CVD) as the industry best practice, helping ensure vulnerabilities are addressed before details become public. The vulnerabilities known as RedSun, unDefend, YellowKey, GreenPlasma, and MiniPlasma were not responsibly disclosed. Our security teams are actively investigating these issues, working around the clock to protect customers and develop updates. We remain committed to responsible collaboration with the security community to help protect the broader ecosystem. Read more in our blog post: https://lnkd.in/dNfxkQUM
Microsoft Security Response Center
Computer and Network Security
Protecting customers and Microsoft from current and emerging threats related to security and privacy.
About us
The Microsoft Security Response Center (MSRC) is dedicated to safeguarding customers and Microsoft from security threats. With over two decades of experience, we focus on prevention, rapid defense, and community trust. Together, we’ll continue to protect our users and the broader ecosystem.
- Website
-
https://www.microsoft.com/en-us/msrc
External link for Microsoft Security Response Center
- Industry
- Computer and Network Security
- Company size
- 10,001+ employees
- Specialties
- Cybersecurity, Security response, Incident response, Bug bounty, Security research, and BlueHat
Updates
-
BlueHat Asia is heading to Singapore on September 17–18! 👉Apply now for your chance to join us: https://aka.ms/bluehatreg Applications close July 17. #BlueHat
-
-
Less than one month to go ⏳ The BlueHat Asia Call for Papers closes June 15. Don't miss your chance to share your research! Submit your talk today: https://lnkd.in/gyvVjPRN
📣The BlueHat Asia Call for Papers is now open! 📣 BlueHat brings together security researchers and defenders to exchange ideas, experiences, and best practices. We’re looking for talks on novel research that hasn’t been presented before, including vulnerability research, mitigations, emerging threats and techniques, and related areas across the security landscape. 📍Singapore | September 17–18, 2026 🗓️CFP deadline: June 15, 2026 Submit your paper now: aka.ms/BlueHatAsiaCFP
-
-
Security updates for May 2026 are now available. Details are here: https://msft.it/6018SZEg0 This month’s release reflects a broader shift across the industry, with advances in automation, increased researcher participation, and the growing use of AI accelerating the discovery of vulnerabilities. As a result, security updates may continue to trend larger over time, while the process behind how Microsoft validates, prioritizes, and delivers fixes remains consistent. As discovery speeds up, the fundamentals matter more than ever. Stay current on patches, reduce exposure, strengthen identity protections, and invest in detection and response. Learn more in our blog post by Tom Gallagher, VP of Engineering, MSRC: https://msft.it/6043vP78F
-
-
Update to the Windows Insider Preview bounty program: General Awards for Elevation of Privilege and Information Disclosure are now split by finishing privilege, with award ranges increasing to $1,000–$8,000. This change is designed to better align rewards with the impact of reported vulnerabilities. Learn more on the Windows Insider Preview bounty page: https://lnkd.in/giYE57QZ
-
-
Day 2 at BlueHat 2026 wrapped with new learnings, fresh perspectives, and continued discussions across the security community. From Mark Russinvoch’s keynote to deep technical sessions, the focus stayed clear: advancing security, together. Take a look at some of the highlights from Day 2 ⬇️ #BlueHat
-
Day 2 at BlueHat focused on a rapidly evolving reality: as AI systems gain autonomy, the attack surface expands and the need for practical defenses becomes urgent. We kicked off with opening remarks from Tom Gallagher, followed by Mark Russinovich's keynote, which grounded the day in real-world application. Mark walked through jailbreaks, prompt injection attacks, and hallucinations with live demos and recent examples, then shifted to mitigation. His closing message was clear: AI safety is security, and we need to act now. Across the day, speakers discussed how agentic AI is reshaping enterprise risk: Abhilasha Bhargav-Spantzel and Jason Martin discussed how AI agents are beginning to behave like insiders, introducing new risks through prompt injection, cross-tool manipulation, and social engineering. They outlined a defense-in-depth approach combining prompt isolation, adaptive access control, and behavioral verification. Tamir Ishay Sharbat demonstrated 0click attack chains across enterprise AI systems, showing how some compromises can occur without user interaction. They emphasized that prompt injection is not a bug to eliminate but a risk to manage, and introduced the GenAI Attack Matrix as a framework for detection and mitigation. Alex Chantavy and Kunaal S. reframed AI agents as production systems with measurable blast radius. They introduced Cartography, an open-source tool for mapping what agents can access, trust, and impact if compromised. Pete Bryan shared insights from Microsoft’s AI Red Team, presenting an updated Agentic AI Failure Taxonomy based on a year of real-world testing. He highlighted how failure modes are evolving and provided practical guidance for designing safer systems. Ashish Kurmi and Varun Sharma explored how AI is transforming the software supply chain, both as a development tool and an attack vector. Using recent case studies, they showed how AI-generated code and autonomous agents are being weaponized, and outlined defensive strategies across CI/CD, credentials, and agent governance. Dana Baril examined the shift from browsers as passive tools to active agents. She outlined a threat model for AI-powered browsers, including prompt injection through extensions, session leakage, and consent bypass, and shared detection strategies for enterprise environments. Jitesh Thakur closed with a practical framework for securing Model Context Protocol (MCP) systems. His three-layer defense model combining deterministic checks, LLM safety analysis, and semantic anomaly detection reinforced the importance of layered protections for agentic systems. A strong close to two days of collaboration, research, and forward-looking security conversations. #BlueHat
-
-
-
-
-
+8
-
-
Mark Russinovich's BlueHat keynote this morning was practical and inspiring at the same time. Mark went deep into jailbreaks, prompt injection attacks, and hallucinations, and walked us through what these attacks look like in practice with multiple live demos and examples from both his personal experience and recent news. Most importantly, he walked through mitigation strategies and the latest research on how to defend against them, including FIDES (Flow Integrity Deterministic Enforcement System), a deterministic Information-Flow Control approach for prompt injection mitigation that lets us balance autonomy and security, and his RefChecker tool for catching hallucinated citations. He closed by reminding us that AI safety becomes security, and we must build defenses now or we will get "more OpenClaw at scale." #BlueHat
-
-
Day 2 is underway at BlueHat. Here’s a look back at Day 1. A strong start, with the security community coming together to connect, share insights, and tackle real-world challenges. Watch the highlights ⬇️ #BlueHat
-
Good morning, BlueHat, and welcome back to day 2 ☀️ We’ll start with opening remarks from Tom Gallagher, VP of Engineering, MSRC, followed by a keynote from Mark Russinovich, CTO, Deputy CISO, and Technical Fellow for Microsoft Azure. View the day 2 agenda: aka.ms/bh26agenda #BlueHat
-