A fundamental flaw leaves LLMs strikingly vulnerable to attack
AI Summary
Researchers have identified a fundamental flaw in large language models that makes them susceptible to hacks, asserting that complete security against attacks is unattainable. This finding, presented at the International Conference on Machine Learning, raises significant concerns regarding the safety of these technologies.
From the source
It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at the International Conference on Machine Learning, a top AI conference, this month. The claim has huge implications for the safety of this technology, which…
The full text couldn't be loaded here (the source may require a subscription).
View original at MIT Tech Review