- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes a purification method for attacking current purification-resistant personalization defenses. Specially, CAPure focuses person-related tokens for diffusion purification, which can recover suppressed person-semantic responses and facilitates subsequent identity associations.
Critical strengths
- This paper considers a new attack for purification-resistant personalisation defences.
- The writing is well and easy to follow.
Critical weaknesses
-
The finding is not surprising because the method of protecting portraits will undoubtedly focus on the face area. Besides, the proposed method largely combines existing cross-attention guidance and reconstruction-based purification. These are existing techniques in personalized diffusion models, e.g., DisDiff, CoPSAM, Attend-and-Excite.
-
The ablation results indicate that reconstruction guidance accounts for most of the identity recovery, whereas the proposed attention guidance provides only modest additional gains. This weakens the claimed importance of the central identity-aware design.
-
The proposed method has extensive iterative denoising and additional gradient computations, yet the paper provides no runtime or computational cost. It remains unclear whether its relatively modest gains over existing purifiers justify the additional cost.
-
The evaluation is concentrated on DreamBooth with Stable Diffusion v1.5. The authors should add generation experiments on other personalization paradigms (such as LoRA) and modern diffusion architectures.
-
In Table1, all defenses do not seem to perform well, such as MetaCloack and HF-ADB under purification. The authors need to illustrate this. Otherwise, the experiments may have some mistakes. In addition, there are many errors in the red and blue markings of Table 1. For example, in the first column, 29.23 is not the best, but it is marked in red.
-
The effect of the method seems to be very weak, especially considering that the focus of this article is on human identity, so ISM should be more important, but it seems that the improvement is very small, such as 0.678 v.s. 0.671, 0.670 v.s. 0.087. This makes the problem described in the article possibly not valid or not so important, because the original DiffPure and other methods will also automatically focus on the face area during the optimization process.
-
The corresponding defense needs to be considered and analyzed, as the purification considered in the article is a kind of attack.
Questions for authors
-
What is the key technical novelty of the proposed method, especially considering the limited contribution of attention guidance in the ablation studies?
-
Why the relatively marginal improvements in identity preservation given the additional computational overhead, and can the effectiveness be demonstrated on LoRA-based personalization and more recent diffusion architectures?
-
Can the authors explain the unexpectedly weak performance of existing defenses in Table 1?