#distillation-attacks

[ follow ]
#ai-model-extraction #cybersecurity-threats #ai-safety #industrial-espionage #model-theft
Artificial intelligence
fromIntelligencer
1 week ago

Why AI Companies Are Suddenly Worried About Theft

Chinese AI firms conducted industrial-scale distillation attacks on Anthropic's Claude model using fraudulent accounts to extract proprietary capabilities at reduced development cost and time.
Artificial intelligence
fromTheregister
2 weeks ago

How AI could eat itself: Using LLMs to distill rivals

Competitors are probing commercial AI models to extract underlying reasoning via distillation attacks to replicate capabilities and lower development costs.
[ Load more ]