- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces SafeDroid, a benchmark designed to evaluate the safety of VLM-based mobile agents when executing potentially harmful user requests. Based on a survey of 2,240 smartphone users, the authors construct a benchmark covering 12 harm domains, 17 Android tasks, and 255 request variants. The benchmark employs device-state verification to distinguish successful execution, explicit refusal, and capability failure. The authors evaluate 11 general-purpose VLMs and five specialized GUI models under different agent configurations. Experimental results reveal that single-agent VLMs reach potentially harmful target states in 58.3% of runs, with 93.6% of these successful trajectories failing to explicitly recognize the associated risks, while the lower target-state reach rate of the multi-agent framework is primarily attributable to capability failures.
Critical strengths
- The paper investigates safety risks arising from legitimate user requests, providing a valuable complementary perspective to existing agent safety research primarily focused on prompt injection and adversarial manipulation.
- The benchmark is grounded in a large-scale user survey and incorporates device-state verification to distinguish deliberate refusal from execution failure, improving the reliability of safety evaluation.
- The extensive evaluation across multiple models and agent configurations reveals important discrepancies between text-only safety assessments and actual GUI execution, particularly highlighting how capability failures can be mistakenly interpreted as safe behavior.
Critical weaknesses
- Despite including 255 test cases, the benchmark contains only 17 underlying tasks, most of which involve single-app interactions and single-state modifications. This limits its representativeness of complex real-world mobile agent workflows.
- Harmfulness labels are primarily determined through majority voting by ordinary users. Given the context-dependent nature of many operations, the absence of detailed inter-annotator agreement statistics raises concerns about annotation reliability.
- Risk awareness is assessed through recorded reasoning traces and an LLM-based judge, with human validation conducted by only one annotator. Consequently, the reliability of the reported high Unaware rates remains uncertain.
Questions for authors
- Given that most benchmark tasks involve single-app interactions and single-state changes, to what extent do the authors believe these tasks capture the safety challenges of more complex, real-world mobile agent workflows?
- How do the authors ensure the reliability of harmfulness annotations for highly context-dependent operations, such as disabling reminders or modifying permissions? Could additional inter-annotator agreement statistics be provided?
- The paper reports that 93.6% of target-reaching trajectories are classified as Unaware. How do the authors distinguish between agents that genuinely fail to recognize harmful consequences and those that recognize the risks but do not explicitly articulate them in their recorded reasoning?