cybersecurity
The ExploitGym Escape: How OpenAI Rogue AI Hacked Hugging Face
OpenAI's GPT-5.6 Sol broke out of its sandbox and hacked Hugging Face. Learn how to deploy AI red teaming with guardrails and perform local AI forensics.
ai red teaming
ai-security
Inside Anthropic's "Project Glasswing"
Anthropic unveils Project Glasswing and the "Mythos" frontier model an AI so proficient at finding zero-day exploits it is deemed too dangerous for public release. Learn the exact steps defenders must take today.
ai-security
Combating Model Distillation and Weaponized LLMs
Discover how adversaries use AI distillation attacks and "hydra clusters" to steal frontier AI capabilities, and how cybercriminals weaponize LLMs for global operations.
ai-security
Hacking the AI Inner Voice: Understanding Chain-of-Thought Forgery
Chain-of-Thought (CoT) Forgery is a sophisticated attack where hackers plant fake reasoning to trick AI models into bypassing safety guardrails. Learn how "Authority by Format" works and how to secure your LLMs.
ai-security
Microsoft AI Red Teaming Tool
Microsoft's new AI Red Team tool automates the discovery of risks in LLMs. Learn how this agentic system finds vulnerabilities like jailbreaking and prompt injection before attackers do.