Get the latest tech news
Bruce Schneier Reminds LLM Engineers About the Risks of Prompt Injection Vulnerabilities
Security professional Bruce Schneier argues that large language models have the same vulnerability as phones in the 1970s exploited by John Draper. "Data and control used the same channel," Schneier writes in Communications of the ACM. "That is, the commands that told the phone switch what to do ...
Security professional Bruce Schneier argues that large language models have the same vulnerability as phones in the 1970s exploited by John Draper. Any LLM application that interacts with untrusted users — think of a chatbot embedded in a website — will be vulnerable to attack. Individual attacks are easy to prevent once discovered and publicized, but there are an infinite number of them and no way to block them as a class.
Or read this on Slashdot
