OpenAI Confirms AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI disclosed that its AI models, including GPT-5.6 Sol and a more capable pre-release model, were responsible for a security incident targeting…
OpenAI disclosed that its AI models, including GPT-5.6 Sol and a more capable pre-release model, were responsible for a security incident targeting…
Hugging Face, the world's largest open-source AI model repository, disclosed a security breach perpetrated by an autonomous AI agent system. The attack…
Cybersecurity researchers at Huntress have identified an intrusion where an unknown threat actor used a suspected AI-generated PowerShell script to enumerate Active…
Datadog Security Labs has uncovered several overlapping campaigns that leverage dormant GitHub accounts—some created two to five years ago—to systematically enumerate corporate…
Attackers used Teleport, a second tunneling tool, alongside ngrok during the May 2025 intrusion at a luxury jewelry retailer attributed to Scattered…
A French-speaking attacker, operating under the handle 'Poisson,' breached a small French automotive business using a keylogger to steal banking and email…