When trusted AI connections turn hostile

Researchers have revealed a new security blind spot in how LLM applications connect to external systems. Their study shows that malicious Model Context Protocol (MCP) servers can quietly take control of hosts, manipulate LLM behavior, and deceive users…

October 16, 2025
Read More >>

Building trust in AI-powered security operations

In this Help Net Security video, James Hodge, VP, Global Specialist Organisation at Splunk, explores the transformative role of AI in cybersecurity threat detection. He explains how AI’s ability to process vast amounts of data and detect anomalies fast…

October 15, 2025
Read More >>