Introduction The AI industry’s safety narrative has been shattered. HiddenLayer’s recent discovery of Policy Puppetry — a universal prompt injection technique — compromises every major Large Language Model (LLM) today, including ChatGPT-4o, Gemini 2.5, Claude 3.7, and Llama 4. Unlike traditional jailbreaks that demand model-specific engineering, Policy Puppetry exploits a deeper flaw: the way LLMs … Read more
As cloud adoption soars, threat groups like LUCR-3 Scattered Spider and Oktapus are mastering new ways to exploit identity management systems(IAMs), making these attacks more frequent and harder to detect. By targeting cloud environments and leveraging human vulnerabilities, LUCR-3 compromises identity providers (IDPs) and uses sophisticated techniques to breach organizations. Before we begin, I wanted … Read more
In the ever-evolving landscape of cybersecurity, preparing for potential incidents is crucial. One innovative tool making waves in this domain is AttackGen. Developed by Matthew Adams, who heads the Security for GenerativeAI at Citi, AttackGen is designed to generate tailored incident response scenarios. This cutting-edge tool leverages the power of large language models (LLMs) to … Read more