- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes PAQ-Diffusion, a post-training quantization method for reducing membership-inference leakage in diffusion models. It first aligns member and non-member quantization residuals at the layer level, then learns timestep-specific activation scales using a denoising-error privacy objective. Experiments on a DDPM and two latent diffusion models show lower attack AUC with similar FID.
Critical strengths
- The proposed idea is reasonable, and the two-stage privacy-aware quantization framework is well-motivated and conceptually clear, without requiring privacy-aware retraining of the full-precision model.
- The evaluation covers three diffusion models and multiple membership-inference attacks, with an ablation separating the layer-wise and timestep-wise stages (Table 4), and reports both AUC and TPR at 1% FPR, making the privacy evaluation more comprehensive.
Critical weaknesses
-
Inconsistencies in dataset split and optimization objective description. The paper contains several inconsistencies in its experimental and methodological descriptions. In Table 5, the reported SD-Laion source pool contains only 2,500 members and 2,500 non-members, while the listed calibration, SecMI-NN auxiliary, and test splits require more samples if they are mutually disjoint as claimed. The authors should clarify the construction of these splits. Moreover, the reconstruction objective appears inconsistent between the main paper and appendix: Eq. (13) defines a squared L2 reconstruction loss, while Appendix A.1.4 states that activation reconstruction uses “ reconstruction”. The relationship between these objectives and the actual implementation should be clarified.
-
Insufficient ablation of the privacy-aware objectives. Although Table 4 shows improvements from both stages, it does not isolate the contribution of the proposed privacy losses from other changes, such as additional optimization and timestep-specific activation scales. In particular, an ablation with the privacy loss removed () under the same optimization settings would help clarify how much of the improvement comes from the privacy-aware objectives themselves.
Questions for authors
-
In Table 5, the SD-Laion auxiliary and test set sizes exceed the available source pool after excluding calibration samples, despite the stated disjointness. Could the authors clarify the construction, intended roles, and overlap status of these splits?
-
In Appendix A.1.4, the authors mention an “ reconstruction” objective, while Eq. (13) uses a squared L2 loss. Is “” a notation error, or does it refer to a different reconstruction objective?
-
Could the authors provide an ablation with the privacy loss removed (), while keeping the calibration data and optimization settings unchanged?
Response to Reviewer vPg8
We thank the reviewer for the constructive feedback and for identifying inconsistencies in our experimental descriptions. We provide clarifications and additional ablation results below.
1. Dataset splits and reconstruction objective (Weakness 1 and Questions 1–2)
Dataset splits. We apologize for the typo in Table 5. The SD-Laion dataset contains 2,500 members and 2,500 non-members, divided into 100/100 calibration samples, 1,000/1,000 SecMI-NN auxiliary samples, and 1,400/1,400 test samples. These three subsets are mutually disjoint, with no overlap between calibration, auxiliary training, and attack evaluation. The reported test size of 2,400/2,400 was a typographical error, which we will correct in the revised manuscript.
Reconstruction objective. We apologize for the inconsistency between Eq. (13) and Appendix A.1.4. The implementation uses the squared L2 reconstruction loss throughout both stages. The reference to a different reconstruction objective in the appendix is a reporting error and will be corrected.
2. Privacy penalty ablation (Weakness 2 and Question 3)
To isolate the contribution of the privacy objectives, we conducted additional ablation experiments on DDPM-CIFAR10 by setting the corresponding privacy coefficient λ=0, while keeping the calibration data, optimization budget, and timestep settings unchanged.
Table R1. Privacy penalty ablation (AUC / TPR@1%FPR, lower is better).
As shown in Table R1, Stage 1 provides the primary privacy improvement, while Stage 2 offers additional protection. Disabling the Stage 1 privacy penalty increases SecMI-NN AUC from 0.6078 to 0.9057, while disabling Stage 2 increases it to 0.8036. When both penalties are disabled, membership leakage increases substantially, approaching the performance of conventional privacy-unaware quantization for several attacks. These results further support the effectiveness of the two-stage privacy-aware quantization framework.