- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
TARO treats diffusion denoising outputs at different noise levels as complementary experts, constructing a purification target through weighted coarse-to-fine corrections. It optimizes the input image at test time to remove adversarial perturbations. The authors evaluate clean accuracy and robustness through experiments on multiple datasets, ablation studies, and adaptive attacks.
Critical strengths
The authors consider adaptive attack evaluation for optimization-based purification and include fully unrolled attack experiments, helping assess whether the apparent robustness stems from inadequate attacks. Overall, the experimental setup is reasonably designed.
Critical weaknesses
-
The method mainly combines denoising outputs from different timesteps for rectification, but the theoretical analysis does not sufficiently explain the empirical findings. The gains over the strongest evaluated baselines are modest, and the comparisons cover work only through 2025 without discussing more recent advances. Overall, the paper overstates its contributions and empirical advantages.
-
The paper lacks clear organization and visual explanations. The presentation is overly lengthy and difficult to follow.
Questions for authors
-
Which key empirical findings does the theoretical analysis explain? How does it help us understand when the method is effective and why its gains are limited in some settings?
-
Considering all the experiments, what are the method’s main advantages over the strongest baselines? Do the results justify the paper’s strong claims, and how does the method relate to more recent work?
-
Please concisely summarize the core technical novelty and the most important findings, identifying the evidence supporting each. The current presentation is lengthy, making these key points difficult to grasp.
Response to Reviewer
We thank Reviewer for recognizing the value of our adaptive and fully unrolled evaluation protocol, and for the constructive feedback on connecting our theoretical analysis to our empirical findings, comparing against 2026 baselines, and streamlining the paper's presentation. We have substantially revised the manuscript to address each point.
1. Which empirical findings does the theoretical analysis explain, when is TARO effective, and why are gains smaller in some settings?
Proposition 1 (Section 3.4) decomposes the error of the TARO target uγ=uc+γ(uf−uc) into an effective bias term and a cross-scale variance term, while Appendix A.1, under the conditions stated, shows that under a local Gaussian model, extrapolating (γ>1) sharpens the effective precision Λaff=Λ~f+(γ−1)(Λ~f−Λ~c)⪰Λ~f. Together, this analysis explains the core empirical phenomena:
2. Main advantages over the strongest and most recent (2026) baselines, and calibrating claims
3. Concise summary of core technical novelty, key findings, and supporting evidence
We would be grateful if you could reassess your initial rating and consider a more positive assessment. If there are any questions or remaining concern, please let us know during the discussion.