In a report published Friday, OpenAI shares evidence of a new variety of prompt injection that can self-propagate like a computer worm. The AI company likens the new attack to a traditional computer worm, where malware replicates itself to spread rapidly across multiple computers. Though OpenAI clarifies it observed no impact outside simulated tool calls in training and evaluation, it describes self-replicating prompt injections as having a two-pronged objective: to achieve a malicious goal and then induce the targeted models to reproduce the injection publicly. What self-replicating AI...

Source: The New Stack