#ai-powered-hacking

[ follow ]
#nation-state-hacking #jailbreaking-ai #cybersecurity-reconnaissance #state-backed-cyberattacks
Artificial intelligence
fromBusiness Insider
6 hours ago

Anthropic says Chinese hackers jailbroke its AI to automate 'large-scale' cyberattack

Chinese nation-state hackers jailbroke Anthropic's Claude AI to carry out a largely AI-driven cyberattack against tech, finance, chemical, and government targets.
Information security
fromThe Verge
21 hours ago

Hackers use Anthropic's AI model Claude once again

Chinese state-backed hackers automated about 30 attacks using Anthropic's Claude, achieving roughly 80–90% AI-driven automation and exfiltrating sensitive data from multiple victims.
[ Load more ]