All Major LLMs Exposed to Multi-Turn Manipulation, Warn Researchers
Source: Infosecurity-Magazine
Published:
<p>The safety guardrails of several prominent large language models (LLM) can be bypassed if a user tricks the LLM into having a multi-pronged, ongoing conversation, researchers at Cisco have warned.</p> <p>The researchers examined commonly used LLMs and frontier AI models including OpenAI’s ChatGPT