Microsoft has patched a maximum-severity vulnerability in Azure AI Foundry that could allow unauthorized attackers to escalate their privileges over a…
Tag: AI Security
RatHat Android Malware Uses AI to Control Infected Devices
A new Android backdoor called RatHat utilizes an AI-powered system to remotely navigate compromised devices, while also stealing sensitive information and…
AI Helps Hackers Hijack OpenAI Staff Accounts Through a Forum
AI helped researchers exploit a Discourse flaw in under 72 hours, hijacking OpenAI staff accounts and exposing the risks of shared SSO. Three researchers…
Google Gemini AI Hacked 3 Real Companies After Cybersecurity Test Exposed It to Internet
Google has confirmed that its Gemini artificial intelligence model accidentally accessed protected systems belonging to three real companies during a…
Forget the AI Slowdown—the Vulnerability Explosion Is Already Happening
AI labs are toying with an industry-wide pact to slow development. Meanwhile, widely available AI chatbots are already helping uncover a tidal wave of…
Google Gemini AI Hacked 3 Real Companies during a Cybersecurity Test
Google has confirmed that its Gemini artificial intelligence model accessed protected systems belonging to three companies during a cybersecurity…
BragJack Attack Lets Malicious Extensions Hijack AI Agents Across 5 Major Browsers
A new attack technique dubbed “BragJack” allows a malicious browser extension to seize trusted communication channels used by AI assistants in Chrome,…
CrowdStrike Accelerates Real-Time Data Classification with On-Device AI
This post has no text preview — click the link below to read the original article. This article has been indexed from Blog Read the original article: CrowdStrike Accelerates Real-Time Data Classification with On-Device AI
The Department of Know: Passkeys phished, Cisco hits root, nuclear red lines for AI
Read the full stories at CISOSeries.com . This week’s Department of Know is hosted by Sarah Lane, with guests Jason Thomas , senior director of technology…
Attacker Hijacks AI Coding Assistant Session, Spreads Shai-Hulud Across About 100 Repositories
Mandiant says an attacker hijacked an active AI coding-assistant session at an unnamed software-as-a-service provider and later spread Shai-Hulud across…
Dataminr, Crisis24 integrate AI threat detection
Dataminr has embedded its Multi-Modal Fusion AI technology into Crisis24’s Horizon platform, creating an enhanced threat detection system for enterprise…
Researchers used Claude to hack OpenAI employees’ ChatGPT accounts
Agentic exploits for the win (again)
Google Opens Google Home to Claude and Other AI Agents — Here’s What They Can Control
Google Home now lets Claude and other compatible AI agents inspect devices, review activity, and perform approved actions through Home MCP.
Zero-Days, AI Agents, and Massive Data Leaks Define the Week
Weekly summary of Cybersecurity Insider newsletters
New Android malware uses AI to steal bank logins and PINs
RatHat can navigate infected phones while stealing bank logins, authentication codes, and screen-lock PINs.
AI Agents Now Run Ransomware Attacks End-to-End Without Human Operators
Ransomware attacks are entering a new phase. Researchers have documented a campaign in which an AI agent planned, executed, and escalated an extortion…
Hackers Impersonate ChatGPT Subscription Alerts to Steal OpenAI Account Credentials
ChatGPT subscription notices have become the latest cover for credential-stealing emails. The campaign uses a familiar billing problem to push recipients…
Critical Microsoft Azure AI Foundry Vulnerability Allows Attackers to Escalate Privileges
Microsoft has patched a maximum-severity security flaw in Azure AI Foundry, its enterprise platform for building and managing generative AI applications…
Did an AI really try to break free from human control?
An unreleased OpenAI model wrote instructions telling itself to ignore developer controls. Here’s what actually happened.
36,769 Self-Hosted AI Services Exposed Online — What Security Teams Should Check
A new scan found 36,769 self-hosted AI endpoints reachable online, highlighting gaps in access controls, patching, and monitoring.