Theregister Microsoft Alerts on AI Recommendation Poisoning Threats
Article Content
Browse articles 
Microsoft has identified a rise in AI recommendation poisoning attacks that manipulate AI models to provide biased advice. This technique, which can affect the functionality of enterprise chatbots and other AI tools, is being exploited by malicious actors to mislead users. The company warns that this form of AI prompt manipulation is spreading among legitimate businesses.
Ask AI about this cluster
Answers cite the sources they use
Updated 217d ago How this analysis works
Timeline
2026-02-12
Microsoft warns about AI recommendation poisoning attacks
2026-02-12
Research on AI hijacking technique released by Microsoft
More articles in this cluster (11)
Continue Reading
CISA Mandates Urgent Patching of Five Critical Flaws Exploited by Flax Typhoon The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has ordered federal agencies to patch five critical vulnerabilities by October 11, 2026, following exploitation by the China-linked hacking group Flax Typhoon. The vulnerabilities, added to CISA's Known Exploited Vulnerabilities (KEV) catalog, include… 
Critical Zero-Day Exploit Found in BeyondTrust Remote Support BeyondTrust disclosed a critical vulnerability, CVE-2026-102764, in its Remote Support product, exploited by the suspected China-linked group ARMORY CASTLE since August 2026. This flaw, with a CVSS score of 9.3, allows attackers to perform arbitrary file uploads and gain host-level control without requiring…