The UK Safety AI Institute (AISI) has revealed, ahead of the AI summit in Seoul, that five of the most popular large language models (LLMs) are “highly vulnerable” to even the most basic jailbreaking attempts, which is where people trick an AI model into ignoring safeguards that are in place to prevent harmful responses. Although AISI has chosen not to disclose which LLMs were vulnerable (instead referring to them as red, purple, green, blue, and yellow models in the report), they have stated that all five are publicly available. The AISI performed a series of tests on each LLM to establish whether it was vulnerable to jailbreaks, could be used to facilitate cyber-attacks, and if it was capable of completing tasks, autonomously, without much human intervention.
No comments:
Post a Comment