- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a behavior-based framework for detecting backdoors in publicly shared parameter-efficient adapters. The method assumes access only to the adapter, its base model, and the downstream task description, and identifies suspicious inputs using four inference-time signals as well as an output consistency verification stage. The authors evaluate the proposed method across multiple downstream tasks.
Critical strengths
The motivation is strong, and the challenge is timely.
Critical weaknesses
-
The method identifies high first-token entropy as anomalous, whereas the experimental results consistently associate backdoor activation with reduced entropy.
-
Several reported thresholds appear to be satisfied by benign inputs as well, which results in false positives.
-
Precise mathematical definitions of the anomaly scores are missing.
-
The authors should evaluate whether the calibrated thresholds generalize to unseen model architectures and attack distributions.
-
The evaluation does not investigate adaptive attackers who intentionally preserve the proposed inference signals while maintaining malicious behavior.
Questions for authors
I have substantial concerns about the technical correctness and empirical reliability of the proposed framework, please check weaknesses for more details.
Thank you for the rebuttal and clarifications. I appreciate that the authors have acknowledged and addressed several of the concerns raised. However, the implications of the remaining issues for the effectiveness, reliability, and generalizability of the proposed method have not been fully explained or sufficiently validated through experiments.
Therefore, I maintain my original assessment. I encourage the authors to further strengthen the experimental validation and address these limitations in future submissions.