- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper investigates the robustness of concept erasure in diffusion models under model merging. The authors distinguish between erasure-update attenuation and partner-update injection, showing that both can restore erased concepts. Through experiments on Stable Diffusion 1.5, the paper compares interpolation, task arithmetic, parameter guards, and re-erasure. The results suggest that strength-tuned addition provides a better suppression–appearance trade-off than interpolation, while parameter guards offer only marginal additional improvements.
Critical strengths
-
The research problem is meaningful. The paper explores an important but relatively underexplored scenario in which concept erasure may be compromised by subsequent model merging, even without adversarial intent.
-
The experimental controls is well-designed. The separation of erasure attenuation and partner injection, together with norm-matched random perturbations, provides useful empirical evidence for understanding concept recovery.
-
The comparison of merging strategies is well-designed. The appearance-constrained evaluation accounts for the trade-off between erasure preservation and appearance transfer, offering practical insights into different merging operators.
Critical weaknesses
-
The paper systematically evaluates concept resurgence under different model merging strategies. However, the underlying mechanisms remain insufficiently explored. For example, while parameter guards improve erasure retention, they often substantially compromise the transfer of partner capabilities. The paper provides limited explanation for this trade-off or insight into how erasure-related and partner-related parameter updates interact. A deeper analysis would strengthen the paper's contributions beyond empirical observations.
-
The experiments are restricted to three benign object concepts, leaving generalization to other kinds of concepts unclear. Additionally, erasure effectiveness relies primarily on classifier scores, while appearance transfer is measured using CLIP similarity, which mixes style, content, and composition. These limitations weaken the reliability and generality of the conclusions.
Questions for authors
-
Could the authors provide further insights into the mechanisms by which partner updates restore erased concepts, beyond the observed differences between structured updates and random perturbations?
-
To what extent do the findings generalize to other concept categories, particularly identities, artistic styles, and harmful content? In particular, it would be interesting to investigate whether artistic style erasure remains effective when the erased model is merged with other style-specific models.