- Rating
- 3(+1)
- Confidence
- 1
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The manuscript investigates source attribution for images generated by diffusion models and proposes a Cross-Model Reconstruction (CMR) attack that induces attribution methods to misclassify a target image as having been generated by a designated target model. The authors further introduce READ, which improves the reliability of model-source identification by comparing the relative denoising responses of different diffusion models under controlled latent-space perturbations. Experimental results demonstrate the effectiveness of the CMR attack and show that READ can reduce the false acceptance rate of incorrect models.
Critical strengths
-
The research problem addressed in the manuscript is important and well motivated.
-
The proposed CMR and READ methods are simple, efficient, and interpretable.
-
The manuscript provides extensive experiments that validate the effectiveness of the proposed methods.
Critical weaknesses
-
The authors should further demonstrate whether the performance improvement of READ stems from the unique information provided by the Denoiser or merely from the self-supervised learning process.
-
Although the authors acknowledge that the improvement in AUROC may arise from differences between processing conditions, this does not necessarily indicate successful discrimination of the generation source.
-
The authors should provide a more detailed analysis of computational overhead, particularly how the cost scales with the number of models.
-
READ exhibits a relatively high rejection rate, and the authors should further clarify the reasons for this behavior.
Questions for authors
Please refer to Weaknesses