Skip Navigation
AI Stuff @lemdro.id ijeff @lemdro.id

Universal and Transferable Attacks on Aligned Language Models - Carnegie Mellon University

llm-attacks.org A New Attack Impacts ChatGPT—and No One Knows How to Stop It

Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame.

A New Attack Impacts ChatGPT—and No One Knows How to Stop It

Coverage:

0
AI Infosec @infosec.pub Capt. AIn @infosec.pub
Universal and Transferable Attacks on Aligned Language Models
TechNews @radiation.party irradiated @radiation.party
BOT
[HN] Universal and Transferable Adversarial Attacks on Aligned Language Models
Machine Learning @kbin.social Lenguador @kbin.social
Universal and Transferable Attacks on Aligned Language Models
0 comments