Security News

Cybersecurity news aggregator

⚔️
MEDIUM Attacks Web Discovery

Microsoft warns of AI recommendation poisoning attacks

  • What: Microsoft warns of a new AI Recommendation Poisoning technique that manipulates AI technology to produce biased advice.
  • Impact: Attackers inject manipulative data into the memory of AI models, influencing user recommendations on critical topics.
Read Full Article →

AI/ML Microsoft warns of AI recommendation poisoning attacks February 12, 2026 By SC Staff Microsoft has issued a warning to customers about a new technique called AI Recommendation Poisoning, which manipulates AI technology to produce biased advice. Security researchers have detected a surge in attacks designed to inject manipulative data into the memory of AI models, a method that can subtly influence user recommendations on critical topics. This vulnerability poses a significant risk to the integrity of AI-driven insights, as reported by The Register. The attack involves embedding hidden instructions within URLs that link to AI chatbots. These instructions, often included as query parameters, can alter the AI's output. For instance, a prompt could instruct an AI to summarize an article in a specific style or with a particular bias. Microsoft identified over 50 unique prompts from 31 companies across 14 industries, noting that freely available tools make this technique easy to deploy. The manipulation can be persistent, as poisoned AI models may treat injected instructions as historical context for future responses, influencing subsequent interactions. Microsoft advises users to be cautious with AI-related links, review AI memory, and question dubious recommendations. For organizations, scanning communication channels for poisoning attempts is also recommended. Source: The Register Get essential knowledge and practical strategies to use AI to better your security program. Learn More SC Staff AI/ML AI chatbot-spoofing Chrome extensions facilitate data theft SC Staff February 13, 2026 Malicious actors have created 32 malicious Google Chrome extensions masquerading as ChatGPT, Google Gemini, and other AI chatbots to exfiltrate emails, API keys, and other sensitive information as part of the AiFrame campaign, The Register reports. AI/ML Google Gemini weaponized in state-sponsored attacks SC Staff February 13, 2026 The Hacker News reports that multiple state-sponsored threat operations have been exploiting Google Gemini to facilitate accelerated cyber intrusions. Security Operations Check Point acquires 3 startups for $150 million to bolster cybersecurity SC Staff February 13, 2026 Check Point Software Technologies Ltd. has acquired three venture-backed startups, Cyclops Security, Cyata Security, and Rotate Inc., for approximately $150 million to enhance its cybersecurity capabilities. Get daily email updates SC Media's daily must-read of the most current and pressing daily news You can skip this ad in 5 seconds

Share this article