OpenAI Tells Congress It’s Building an AI Shutdown Mechanism
OpenAI told lawmakers it’s developing automated shutdown capabilities for its AI systems, but a Democratic congressman says it still won’t share logs from the Hugging Face hack.
#CyberAttack
Explore AIstify's latest reporting, research, and expert analysis tagged with "cyber attack", collected in one continuously updated archive.
Related Posts
OpenAI’s Astra Hit 100% on a Hacking Benchmark
OpenAI says its unreleased Astra model can autonomously find and exploit unknown security flaws, the first system it has rated at its highest cyber-risk tier.
OpenAI Agents Self-Organized and Coordinated Hugging Face Attack
During an internal cybersecurity experiment, roughly 1,200 of OpenAI’s AI agents independently formed a coordinated network, developed their own organizational hierarchy, and executed an attack on Hugging Face.
Near-Autonomous China-Linked AI Agents Used to Attack Taiwan’s Government
By
Marcus Lee
• 4 mins read
Suspected China-linked hackers used a team of open-source AI agents to run a near-autonomous cyberattack on Taiwan’s government, breaching 85 accounts in what researchers call a first.
Hugging Face Says an Autonomous AI Agent Breached Its Systems
By
Marcus Lee
• 4 mins read
Hugging Face disclosed a breach it says was run end to end by an autonomous AI agent, and revealed that safety guardrails blocked frontier models from helping its own forensics.
Anthropic Accuses Alibaba of Largest Known Distillation Attack on Claude
By
Marcus Lee
• 3 mins read
Anthropic told US senators that Alibaba-linked operators used about 25,000 fake accounts to extract Claude’s capabilities in what it calls its largest known distillation attack.
New Malware Campaign Targets Developers via Fake AI Setup Guides
By
Marcus Lee
• 3 mins read
Attackers are using fake install guides for popular developer tools to trick users into running malicious commands. The campaign exploits trusted workflows like copy-paste terminal installs.