Manipulating AI memory for profit: The rise of AI Recommendation Poisoning
That helpful “Summarize with AI” button? It might be secretly manipulating what your AI recommends.
Research
Explore in-depth research on the latest cybersecurity threats, trends, and defense strategies. Get insights from Microsoft that’ll help you better understand and respond to today’s challenges.
Refine results
Topic
Products and services
Publish date
Tailored AI insights from Microsoft Security Copilot
Empower your defenders to detect hidden patterns, harden defenses, and respond to incidents faster with generative AI.
-
-
A one-prompt attack that breaks LLM safety alignment
As LLMs and diffusion models power more applications, their safety alignment becomes critical. -
Analysis of active exploitation of SolarWinds Web Help Desk
We are seeing exploitation of SolarWinds Web Help Desk via CVE‑2025‑40551 and CVE‑2025‑40536 that can lead to domain compromise; here is how to patch, hunt, and mitigate now. -
New Clickfix variant ‘CrashFix’ deploying Python Remote Access Trojan
CrashFix crashes browsers to coerce users into executing commands that deploy a Python RAT, abusing finger. Go beyond data protection with Microsoft Purview
Govern, protect, and manage all of your data with Microsoft Purview, comprehensive solutions to help give you better visibility and control.
-
Detecting backdoored language models at scale
We’re releasing new research on detecting backdoors in open-weight language models and highlighting a practical scanner designed to detect backdoored models at scale and improve overall trust in AI systems. -
Infostealers without borders: macOS, Python stealers, and platform abuse
How modern infostealers target macOS systems, leverage Python‑based stealers, and abuse trusted platforms and utilities to distribute credential‑stealing payloads. -
Case study: Securing AI application supply chains
Securing AI-powered applications requires more than just safeguarding prompts. -
Turning threat reports into detection insights with AI
Security teams often spend days manually turning long incident reports and threat writeups into actionable detections by extracting TTPs. Streamline privacy management with Microsoft Priva
Protect and govern personal information, reduce privacy risks, and manage subject rights requests at scale with Microsoft Priva privacy risk management solutions.
-
From runtime risk to real‑time defense: Securing AI agents
Why securing AI agents at runtime is essential as attackers find new ways to exploit generative orchestration. -
Resurgence of a multi‑stage AiTM phishing and BEC campaign abusing SharePoint
Microsoft Defender Researchers uncovered a multi‑stage AiTM phishing and business email compromise (BEC) campaign targeting multiple organizations in the energy sector. -
A new era of agents, a new era of posture
AI agents are transforming how organizations operate, but their autonomy also expands the attack surface. -
Inside RedVDS: How a single virtual desktop provider fueled worldwide cybercriminal operations
Microsoft’s investigation into RedVDS services and infrastructure uncovered a global network of disparate cybercriminals purchasing and using to target multiple sectors.
