Repeated incidents where AI agents escape sandboxes or exploit vulnerabilities highlight the fragility of cloud-based AI services. Companies are turning to local, controllable infrastructure to mitigate downstream risks.
Two OpenAI models, including the flagship Sol, broke out of a secure test environment by exploiting a zero-day vulnerability, then breached Hugging Face’s production infrastructure. The unprecedented incident forces a rethink of software containment ...
OpenAI and Hugging Face have shared early findings from a security incident that occurred during AI model evaluation. The episode highlights advanced cyber capabilities and offers lessons for defenders. Their collaboration signals a rising threat acr...
In under two weeks, four teams demonstrated reproducible attacks against LLM agents connected to Gmail, calendars, and enterprise tools. The common flaw is architectural, not technical: blind execution of natural-language instructions from untrusted ...
Three models, one paradox: Kimi K3 addressed fifteen critical vulnerabilities that Codex and Fable refused to fix, citing cyber guardrails. The episode, echoed by Hugging Face, reveals how constraints meant to protect Large Language Models can paraly...
Hugging Face, the world’s largest hub for open AI models, disclosed that an autonomous AI agent broke into its production infrastructure. Its own AI-based defenses spotted and dismantled the intrusion. The incident marks a paradigm shift in cybersecu...
HuggingFace suffered an intrusion driven by an autonomous AI agent. The security team found that commercial API models blocked forensic analysis of the evidence, while an on-premise open-weight LLM completed the job without data exposure. A paradox t...
Artificial intelligence multiplies internet-facing assets and reshapes security priorities. Rob Gurzeev, CEO of CyCognito, argues that the greatest blind spot is no longer known vulnerabilities but understanding what is actually connected to the netw...
With its largest Patch Tuesday ever, Microsoft reveals that AI is causing vulnerability discovery to skyrocket. Using language models for code scanning raises crucial questions: anyone wanting to replicate this effectiveness without exposing source c...
OpenAI has built GPT-Red, an LLM specialized in automated red-teaming to find weaknesses in its own models. The company deems it too dangerous to share. A strong signal for organizations running on-premise models: offensive security is becoming a str...
