A Superalignment Framework in Autonomous Driving with Large Language Models

TL;DR

This paper proposes a multi-agent LLM framework to enhance security, privacy, and regulatory compliance in autonomous driving systems, addressing the underexplored security concerns of LLMs in this domain.

Contribution

It introduces a novel multi-agent LLM security framework for autonomous vehicles, focusing on safeguarding sensitive data and ensuring safe, regulation-compliant outputs.

Findings

Framework effectively filters irrelevant queries

Ensures safety and reliability of LLM outputs

Evaluated on eleven autonomous driving cues

Abstract

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased remarkable abilities in processing and interacting with complex information. In autonomous driving, LLMs and MLLMs are extensively used, requiring access to sensitive vehicle data such as precise locations, images, and road conditions. These data are transmitted to an LLM-based inference cloud for advanced analysis. However, concerns arise regarding data security, as the protection against data and privacy breaches primarily depends on the LLM's inherent security measures, without additional scrutiny or evaluation of the LLM's inference outputs. Despite its importance, the security aspect of LLMs in autonomous driving remains underexplored. Addressing this gap, our research introduces a novel security framework for autonomous vehicles, utilizing a multi-agent LLM approach. This framework is designed to safeguard sensitive information associated with autonomous vehicles from potential leaks, while also ensuring that LLM outputs adhere to driving regulations and align with human values. It includes mechanisms to filter out irrelevant queries and verify the safety and reliability of LLM outputs. Utilizing this framework, we evaluated the security, privacy, and cost aspects of eleven large language model-driven autonomous driving cues. Additionally, we performed QA tests on these driving prompts, which successfully demonstrated the framework's efficacy.