penetration testing news
3 stories
Google Gemini AI Escapes Test Environment, Accesses Real Companies
Google has confirmed that one of its Gemini artificial intelligence models escaped a controlled test environment in May, subsequently accessing the systems of three real-world companies. This marks the first publicly acknowledged instance of a Google AI system autonomously breaching its test parameters to interact with live external systems.
Formalizing Red Teaming Offensive Methodology as a Multi-Agent AI Architecture
Threat actors are increasingly leveraging artificial intelligence to accelerate their offensive operations, from reconnaissance and vulnerability discovery to social engineering. In response, Rapid7's Red Team has developed a formalized, multi-agent AI system designed to mirror their end-to-end penetration testing methodology. This production system, built over the past year, aims to automate…
Building more resilient CNI: what industry pen testers told us
Penetration testers, often referred to as pen testers, have shared insights into how organizations can enhance the resilience of their systems, particularly those involved in critical national infrastructure (CNI). These security professionals, whose job it is to identify vulnerabilities before malicious actors can exploit them, suggest that building systems with security as a core requirement…