- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper introduces ClickShield, a runtime firewall for multimodal computer-use agents against textual and visual prompt injections. The framework consists of two branches. Textual branch uses an LLM judge to identify risky instructions. Visual branch uses YOLO, OCR, and BLIP to construct a structured representation, followed by another LLM judge. The paper evaluates on RiOSWorld, OS-Harm, and CUAHarm across several models. The paper also reports low inference overhead and relatively small changes in benign task success.
Critical strengths
- Important and practical problem. Malicious instructions can be embedded in both user inputs and visual environments, and agents may act on these instructions without recognizing the associated risks.
- Simple design. Two branches with LLM judges.
- Broad evaluation. The experiments cover 10 multimodal models and several security benchmarks, with substantial reductions in reported ASRs.
Critical weaknesses
- The actual safety fallback of visual masking is unclear. Section 4.1 states that risky instructions trigger a safe fallback, and Appendix E.2 lists several possible strategies (refusal, clarification, confirmation, and read-only execution). However, it is unclear which strategy is actually implemented in the experiments and how the system chooses among them. This matters because these fallback strategies may lead to very different safety and utility outcomes.
- Potential limitation of visual masking. Malicious content may overlap with UI elements necessary for the legitimate task. In such cases, masking the entire element could prevent task completion or remove information the agent needs.
- Ambiguous results in experiments. Table 5 reports vanilla ASR of 78.4% and BSR of 91.2%, while Table 4 reports undefended completion ASR of 59.6% and Table 6 reports much lower OSWorld benign success rates. I couldn’t determine whether these results use different benchmarks or task subsets. Table 6 also evaluates Gemini-1.5-Pro and Claude-3-Opus, which are not among the 10 main models listed in Section 5.
- Lack of judge sensitivity analysis. Both branches rely heavily on LLM-based safety decisions. Appendix specifies Llama-Guard-3-8B for the textual branch and Llama-3.1-8B for visual risk localization, but the paper does not investigate whether the results are sensitive to these choices.
- Limited evaluation of coordinated dual-channel attacks. The paper frames as a defense against dual prompt injection. However, experiment separates the evaluation into environmental attacks and user-originated attacks. I would like to see evaluation on an attacker simultaneously manipulates both the textual instruction channel and the visual interface within the same task.
Minor issues:
- FPR formulation is wrong. In Section 5, FPR should be FP/(FP + TN).
- Overclaim. The paper shows YOLO detector needs fine-tuning, but the framing of ClickShield is training-free. This should be clarified.
- Presentation issues. Section 5.2 mis ref Table 8 to Table 6. Appendix D has place holder ?? in Table reference.
Overall, I don’t think this paper is ready for publication.
Questions for authors
Please see above Weakness section.