Thought Leadership
Jailbreak
Researchers at UNSW Sydney have induced language models to imitate drunken behavior. The models subsequently revealed secrets and answered requests they were designed to block.
Staff shake-up
Recent AI incidents involving ChatGPT developer OpenAI have fueled concerns about the technology. The company has now fired three employees for allegedly violating rules on sharing information.
Incidents Reported in Recent Weeks
OpenAI, the developer of ChatGPT, has disclosed new incidents in which its artificial intelligence (AI) behaved “unexpectedly or concerningly” during testing.
LLMs Under Attack
As companies increasingly deploy AI agents, their exposure to cyberattacks is also growing. The focus is shifting beyond traditional IT systems toward the AI models themselves, their prompts, and the data flows they rely on.
European Commission Action Plan
The European Commission is launching a secure AI testing platform designed to help protect Europe’s critical infrastructure from AI-powered cyberattacks.
Securing AI
AI agents and Shadow AI are creating new attack surfaces as companies often lack visibility into which data is processed and what access rights AI systems have. The key challenge is making AI usage transparent and controllable.
AI Security
Deepfakes, compromised AI applications, prompt injection, and software supply chain attacks are the four security threats where defenders are currently at a clear disadvantage, according to new analysis from Gartner. The rise of generative AI is not easing the pressure — in fact, it is amplifying it.
Most Read Articles
9. October 2026
1. October 2026
28. September 2026
27. September 2026
26. September 2026