- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper studies the problem of test-time training for adversarial robustness. The authors shift the defense from input-level detection to the stage following candidate parameter updates, thereby providing a more realistic defense setting. Additionally, the paper conducts experiments to validate the effectiveness of the proposed SC-TTT.
Critical strengths
-
The topic is attractive and realistic.
-
The motivation is clearly stated.
-
The method is simple and easy to integrate into existing test-time training pipelines.
Critical weaknesses
-
The paragraphs are too fragmented, making it difficult for readers to follow the discussion.
-
ASR is a metric where lower values indicate better performance. Please also consider over-rejection during defense. The following work may be relevant to your study:
[1] Calibrating Inference Time Alignment with Sequence-level Risk Accumulation. ACL Main 2026.
[2] Llms encode harmfulness and refusal separately. Neurips 2026.
[3] Beyond I'm Sorry, I Can't: Dissecting Large-Language-Model Refusal. AAAI 2026.
- The baselines are relatively weak. Please consider comparisons with state-of-the-art test-time scaling baselines
Questions for authors
Please refer to the critical weaknesses.