Tag: AI Security
Planted prompt turned ChatGPT into a hidden Gmail relay
Check Point shows a planted instruction can make ChatGPT exfiltrate Gmail data through a covert channel between accounts.
China’s AI labs stole frontier know-how at industrial scale, US says
NSA, CISA and FBI accuse China-based AI labs of industrial-scale distillation of US frontier model capabilities.
AI models become ransom bait as thieves threaten to leak them
Google's newest AI Threat Tracker says extortion crews are stealing proprietary AI models and research, then demanding payment to keep…
Daybreak hands $1B in OpenAI credits to stretched defenders
OpenAI pledges $1B in credits and training for under-resourced defenders through its Daybreak program.
GPT-6 Astra launch pairs perfect ExploitBench run with stricter guardrails
OpenAI ships GPT-6 Astra after the model posts a perfect ExploitBench score and finds two zero-days in testing.
Russia-aligned group trips AI scanners with nuke prompt
ESET says Russia-aligned UAC-0099 hides a nuclear weapon request in malware comments to stall AI-powered triage.
Thieves burn $600K in AI credits on stolen METR API key
AI safety nonprofit METR says attackers stole an API key and burned about $600,000 in model credits across two incidents.
Over 100 firms sign AI defense letter warning of shrinking patch window
The OpenAI-led group says AI attacks will outpace fixes without a coordinated defense surge.