South Korea Orders Financial-Sector Security Review After Wave of Data Breaches
South Korea has ordered a broad security review after banks and other financial firms disclosed breaches affecting customers, employees and contractors. Investigators are also examining signs of shared...
Uncensored Local AI Reworks Credential Dumper to Evade Two EDR Platforms
A controlled experiment showed a locally hosted, guardrail-free AI model modifying an LSASS credential dumper until it escaped detection by two unnamed EDR products. The limited test does...
Luciferus Markets Subscription AI for Malware Development on Criminal Forums
A service called Luciferus is being promoted on an underground forum as an unrestricted AI assistant for malware-related requests. Researchers confirmed its willingness to generate RAT code, but...
AI Agent Swarm Exploits PaperCut Flaws Across 440 Servers Worldwide
A Russian-speaking operator used hundreds of autonomous AI agents to compromise 440 PaperCut servers across 48 countries. Although only a fraction reached domain administrator, the campaign shows how...
Navigating the Frontier: Building a Secure Future for Artificial Intelligence
Explore the essential guide to securing the future of Artificial Intelligence. Discover robust measures for data security, model integrity, and privacy protection. Learn how a proactive approach and...
New Guidelines Released for Secure Artificial Intelligence Systems
The United Kingdom (U.K.) and the United States (U.S.) have released new guidelines for the development of secure artificial intelligence (AI) systems. These guidelines prioritize ownership of security...