Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats
Mar 13, 2024
Large Language Model / AI Security
Google's Gemini large language model (LLM) is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks. The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Google Workspace as well as companies using the LLM API. The first vulnerability involves getting around security guardrails to leak the system prompts (or a system message), which are designed to set conversation-wide instructions to the LLM to help it generate more useful responses, by asking the model to output its "foundational instructions" in a markdown block. "A system message can be used to inform the LLM about the context," Microsoft notes in its documentation about LLM prompt engineering. "The context may be the type of conversation it is engaging in, or the function it is supposed to perform. It helps the LLM generate more appropriate responses....
