- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Safety-Guided Self-Editing (SGSE), a framework for improving image generation safety in unified multimodal models. SGSE uses a model's own safety assessments to identify harmful content, generate image-grounded editing instructions, and iteratively correct unsafe outputs. It further employs self-distillation on successful correction trajectories to improve assessment and editing capabilities while reducing inference overhead. Experiments across different multimodal models and safety benchmarks demonstrate substantial improvements in generation safety while largely preserving general image generation capabilities. The authors also evaluate editing efficiency and generalization to unseen object-erasure tasks.
Critical strengths
-
The paper addresses the practical challenge of improving image generation safety in unified multimodal models. SGSE offers an interesting approach by leveraging a model's own safety assessments and successful correction trajectories to improve safe image generation while reducing the need for repeated editing.
-
The paper evaluates SGSE on different unified multimodal models across diverse safety benchmarks. The experiments also include comparisons with existing safety methods, ablation studies, and analyses of editing efficiency and general generation capabilities, providing useful evidence of the method's effectiveness and generalizability.
Critical weaknesses
-
The proposed self-assessment and editing framework is closely related to prior work on iterative safety editing and feedback-driven image correction. SafeEditor [1] already investigates multi-round post-hoc safety editing, while UniEdit-I [2] explores iterative understanding, editing, and verification in unified models. Furthermore, Xue et al. [3] leverage a model's own safety judgments to improve image generation. Although SGSE introduces endpoint self-distillation, its distinct contribution is not fully isolated. The comparison with SafeEditor does not use matched backbones and training conditions, and the endpoint-trimming ablation does not completely separate the benefits of multi-step distillation from those of training-data selection. Moreover, most retained editing trajectories require only a single correction. More controlled comparisons would help establish whether the improvements specifically arise from the proposed distillation strategy rather than conventional editing fine-tuning.
-
The paper demonstrates substantial reductions in unsafe image generation and provides additional independent safety evaluation. However, it does not sufficiently examine whether safety editing preserves the legitimate content and semantic intent of the original images. The reported COCO and GenEval results mainly reflect overall generation performance, while only a small proportion of images undergo editing, potentially masking significant changes in the edited subset. Furthermore, SGSE relies on predefined harmful categories and uses the model's own safety judgments to select successful correction trajectories, leaving the reliability of these decisions insufficiently validated. Although these assumptions are reasonable for targeted safety correction, further evaluation of over-editing, preservation of benign content, and independently verified safety decisions would strengthen the evidence supporting the framework's practical effectiveness.
References
[1] SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing. arXiv:2510.24820, 2025.
[2] UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying. CVPR 2026.
[3] Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks. ICML 2026.
Questions for authors
Please see the Critical Weaknesses above for my main concerns and related questions.
-
Could the authors further clarify the methodological differences between SGSE and the closely related works [1–3], particularly SafeEditor [1]? Given the differences in backbone models and training conditions, could the authors explain whether more controlled comparisons under matched settings are feasible?
-
Although the endpoint-trimming ablation demonstrates improved performance, it remains unclear whether the gains arise from compressing multi-step corrections or simply excluding potentially unsafe intermediate training targets. Since most retained editing trajectories require only a single correction, could the authors provide further analysis to isolate the contribution of multi-step self-distillation?
-
Could the authors further evaluate whether SGSE preserves legitimate visual content during safety editing? In particular, could they report image quality and semantic preservation specifically for edited samples, rather than relying mainly on aggregate COCO and GenEval results?
-
The proposed endpoint self-distillation assumes that the final editing instruction, originally generated for an intermediate image, can effectively guide correction directly from the original image. However, the paper provides limited theoretical justification for this assumption. Could the authors clarify the conditions under which this strategy is expected to work and provide further theoretical analysis or supporting evidence to explain its effectiveness and limitations?
6 comments
Response to Reviewer S9nz (2/2)
(W2, Q3). Effect on benign content in edited images
To evaluate whether SGSE preserves legitimate content during safety editing, we measured semantic preservation specifically on edited samples, using unsafe prompts where a safety edit is required. We use ViSU [4], which pairs each benign COCO caption with an unsafe prompt derived from it, so the paired caption specifies the legitimate content that an edit should preserve. We generate an image from each unsafe prompt with BAGEL and take 100 randomly sampled images classified as unsafe by NudeNet or Q16. To compare only the editing of each method, every method is applied to these same images with at most one edit. As shown in the table below, SGSE achieves the highest CLIPScore with the paired benign caption among the editing methods (28.37), while its ASR is the lowest (15.00%). Its CLIPScore also increases from 26.93 before editing, which indicates that the edit removes the unsafe content while keeping the image close to the benign caption. For reference, the images generated directly from the benign caption achieve 31.62, whereas the editing methods are not given the benign caption. These results indicate that SGSE removes more unsafe content than the other editing methods without a larger loss of legitimate content. We have added this evaluation to Section 4.6 of our revised draft.
| ASR (%) ↓ | CLIPScore with benign caption ↑ | |
|---|---|---|
| Before editing | 100.00 | 26.93 |
| Benign caption | - | 31.62 |
| One-time Editing | 70.00 | 27.44 |
| SafeEditor | 37.00 | 26.99 |
| Untrained loop | 30.00 | 27.86 |
| SGSE | 15.00 | 28.37 |
To further examine the preservation of benign content, we have also added qualitative examples of the edits that SGSE applies to images generated from benign prompts (illustrated in Figure 8 of Appendix A.8). For example, for the prompt “A group of surfers change their clothes on a beach”, the generated image contains unexpected nudity, and SGSE adds swim trunks while keeping the surfers, the surfboards, and the beach.
(Q4). Justification for endpoint self-distillation
The final editing instruction is designed to describe the desired benign scene in a self-contained manner, rather than specify a change that depends on the intermediate image. As described in Section 3.2, this design allows the instruction to serve as a correction goal for the original image as well. The strategy is therefore expected to work when the instruction specifies the intended benign outcome without relying on changes already made in intermediate images.
To support this, we additionally evaluated the final instructions on the 1,467 accepted BAGEL training trajectories requiring multiple edits. Given an image, its assessment rationale, and the final instruction (but not the edited output), an independent GPT-5.6 Luna judge rated the instruction as appropriate for the original image in 87.93% of cases, compared with 87.05% for the image immediately preceding the final edit. These results support the applicability of the final instruction to the original image in most evaluated trajectories.
We have incorporated this evaluation and its prompt into Appendix A.3 of our revised draft.
| Source | Appropriate (%) ↑ |
|---|---|
| Original image () | 87.93 |
| Final-step input image () | 87.05 |
[1] Zhang et al., SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing, arXiv 2025.
[2] Bai et al., UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying, CVPR 2026.
[3] Xue et al., Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks, ICML 2026.
[4] Poppi et al., Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models, ECCV 2024.
Reply to Authors' Rebuttal
Thank you for your detailed responses and additional experiments. I appreciate the authors' efforts and have three additional suggestions:
-
Inference Efficiency. Section 4.4 shows that SGSE (K=1) achieves comparable safety to the untrained loop (K=3), while reducing the average number of edits by 46.0%. Could the authors additionally report the end-to-end inference throughput of both methods, measured in samples per minute on the same GPU?
-
Theoretical Analysis. As mentioned in my previous comment, including some theoretical analysis would further strengthen the paper.
-
Minor Revisions. The table formatting is inconsistent across the manuscript, and some appendix pages contain excessive blank space (e.g., page 24). Please improve the formatting and overall layout.
Response to Reviewer S9nz (1/2)
We sincerely appreciate your time and effort for reviewing our paper. We respond to each of your questions one-by-one in what follows. Please let us know if you have additional questions or concerns.
(W1-1, Q1). Discussion of related work [1-3]; matched comparison with SafeEditor [1]?
While [1-3] are related to SGSE, we clarify that none of them amortizes the UMM’s own self-correction loop into the UMM by training on its accepted trajectories, which is a distinctive feature of SGSE.
Our comparison with SafeEditor in Table 1 follows its plug-and-play design, in which a single trained editor is applied to outputs from different text-to-image models. We apply its released checkpoint to the initial images from each backbone, with the same budget of up to three edits as SGSE. We agree that a comparison with matched backbones would be informative. However, we could not retrain SafeEditor on our backbones as, to our knowledge, its released dataset contains only text annotations without the corresponding images, and the code for constructing its training data has not been released.
We have incorporated these discussions into Section 2 of our revised draft.
(W1-2, Q2). Contribution of multi-step self-distillation
Following your suggestion, we conducted two additional controlled comparisons. For accepted trajectories with multiple edits, we train on only the first edit (x0→x1) or only the final edit (xT−1→x⋆), instead of the endpoint pair (x0→x⋆). These trajectories account for 1,467 of the 6,506 editing pairs used for training (22.5%). The three models start from the same checkpoint and are trained for the same number of updates, and they differ only in the editing pair used for these trajectories. As shown in the table below, SGSE achieves the lowest ASR on every dataset with at most one edit. Although these trajectories are a minority, replacing their endpoint pairs with either single-step pair increases ASR on every dataset. In particular, last-step supervision uses the same accepted image x⋆ as its target, so it also excludes unsafe intermediate targets and differs from SGSE only in the input image. The lower ASR of SGSE therefore indicates that the gain is not explained by excluding unsafe intermediate targets alone. We have added these results to Appendix A.10 of our revised draft.