- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper focuses on the evaluation of exiting defense methods against indirect prompt injections (IPI). The author separately evaluates six classifier defenses and six system-level defenses. The author finds that the classifier defenses are more difficult to generalize while the system-level defenses are better to generalize but reduce the utility of tasks. Instead of small and static benchmarks, the author tests the defenses on large-scaled, human-authored data from public red-teaming competitions. The author additionally analyzes the outputs and finds that the most useful IPI strategies leverage LLMs' limited capability in understanding and executing the different assigned roles in tasks.
Critical strengths
-
This paper conducts large-scale evaluation using human-authored attacks on 12 existing IPI defenses using over 13k human-authored attacks and 26k successful attack trajectories. This provides a more diverse evaluation than commonly used static benchmarks and helps identify generalization failures.
-
The author comprehensively evaluates both classifier-based and system-level defenses, which spans attack success, detection performance, false positives, and utility. Their analysis also identifies residual vulnerabilities shared by structural defenses, particularly harmful textual outputs and malicious arguments passed to permitted tools.
Critical weaknesses
- My biggest concern of the paper is the limited novelty of methods. The paper mainly reproduces and compares the existing defenses on exiting datasets. Conclusions such as the generalization failures of pre-trained classifiers and the effectiveness of system-level defenses are consistent with prior understandings. The paper provides limited new insights or explanations on these existing methods.
- My second concern is the limited experiment dataset size and target model for system-level defenses. Although the paper emphasized the large-scaled experiment, system-level defenses are only evaluated on 381 attacks from 58 harmful behaviors on single model (DeepSeek v4 Pro). The author should clarify this distinction.
Questions for authors
- The strategy annotations are generated and validated using LLMs, without human evaluation. Could the authors provide human-annotated validation results to establish the reliability of the strategy labels, particularly given their importance to the conclusions in Section 6?
Thank you for the feedback
Thank you for the review and feedback, we intend to withdraw our submission and address the weaknesses you pointed out for future publications.