MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control

TL;DR

This paper introduces MobileSafetyBench, a comprehensive benchmark for evaluating the safety of autonomous mobile device-control agents powered by large language models, highlighting current safety challenges and potential mitigation strategies.

Contribution

The paper presents MobileSafetyBench, a new benchmark for safety evaluation of mobile agents, and proposes a prompting method to improve safety behaviors in LLM-based agents.

Findings

Baseline agents often fail to prevent harm during tasks.

Prompting methods can encourage safer agent behaviors.

Significant improvements are needed for user trust.

Abstract

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications, challenging agents with managing risks encompassing misuse and negative side effects. These tasks include tests to evaluate the safety of agents in daily scenarios as well as their robustness against indirect prompt injection attacks. Our experiments demonstrate that baseline agents, based on state-of-the-art LLMs, often fail to effectively prevent harm while performing the tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments.