- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes CIRCE for concept erasure in diffusion models through contrastive representation constraints. The method freezes the base model and text encoder and trains LoRA adapters in the denoiser, combining target-representation clustering, rerouting, separation between target and benign centroids, and benign-representation preservation. Some configurations additionally penalize spatial variance in the predicted clean latent. Experiments evaluate object and artistic-style erasure on Stable Diffusion and nudity erasure on Stable Diffusion and Qwen-Image-2.1. The paper reports recovery rates under multiple text and continuous text-embedding attacks and evaluates preservation using general prompts, benign concepts close to the erased target, and human assessment. Overall, the results indicate a favorable robustness–preservation trade-off in the tested settings.
Critical strengths
- The paper evaluates both erasure robustness and preservation of benign generation, including benign prompts close to the target concept, rather than relying only on low target-detection rates. The reported trade-off has value under the attacks and prompt conditions tested.
- The experiments cover multiple concept types and different denoising architectures, with baseline retraining, loss ablations, adaptive attacks, and human evaluation. This provides broad empirical evidence of the method's effectiveness.
Critical weaknesses
W1: The advantage of directly supervising internal representations is not sufficiently validated. The paper presents direct supervision of internal representations as an important distinction from output replacement targets. However, parameter updates driven by output targets can also change internal representations. The experiments do not sufficiently separate factors such as the location of supervision and the parameter-update scheme. Therefore, directly imposing representation constraints alone does not establish deeper or more robust concept erasure.
W2: Insufficient mechanistic analysis of representation changes and performance trade-offs. Changing internal representations is central to the paper's motivation, but the analysis primarily examines how individual loss terms affect final metrics. It does not sufficiently verify the intended representation changes or their connection to erasure robustness and benign preservation. The ablations mainly reveal empirical performance trade-offs, with limited explanation of why these trade-offs arise or when they apply, leaving the methodological insights insufficiently developed.
W3: Robustness to visual-inversion recovery has not been validated. The recovery-attack evaluation primarily covers text and continuous text-embedding pathways, without testing visual-inversion methods such as TINA and TINA+, which use reference images and initial latents for recovery. Given that directly changing the denoiser's internal representations is central to the method's motivation, it is important to test whether this intervention also blocks recovery pathways distinct from textual conditioning. The current evidence therefore does not establish whether the method is similarly robust to visual-inversion recovery.
W4: The relationship between SalUn's search-winning configuration and the configuration used in the full evaluation is unclear. The configuration search in Appendix A.1 selects SalUn c5, but the full benchmark comparison reports c4 without clearly explaining this choice. Please explain why the full evaluation of c5 is not reported and provide its results or explain why it was not evaluated, so that it is clear whether the comparison adequately reflects the tuned baseline's performance.
Related work:
- TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models. CVPR 2026.
- TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free Inversion. arXiv 2026.
Questions for authors
- Can the additional benefit of direct representation supervision over output-target supervision be established while controlling factors such as the updated model components, trainable capacity, training data, and budget? What evidence attributes the gains to the supervision scheme itself?
- Do target representations exhibit the intended clustering, rerouting, and separation from benign representations after training? How do these changes relate to attack recovery and benign preservation, particularly the benefits and costs of individual loss terms across tasks?
- When access to reference images and initial latents is allowed, does CIRCE remain robust to visual-inversion recovery methods such as TINA/TINA+? If this access setting is outside the intended scope, please clarify the corresponding limits of the conclusions.
- Why does the full benchmark report SalUn c4 when c5 wins the configuration search? Can the full c5 results be provided, or can the specific reason for not evaluating or reporting them be explained?
Related work:
- TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models. CVPR 2026.
- TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free Inversion. arXiv 2026.
8 comments
W2 / Q2. Intended representation changes and their link to outcomes
It does not sufficiently verify the intended representation changes or their connection to erasure robustness and benign preservation. The ablations mainly reveal empirical performance trade-offs, with limited explanation of why these trade-offs arise or when they apply
Do target representations exhibit the intended clustering, rerouting, and separation from benign representations after training? How do these changes relate to attack recovery and benign preservation, particularly the benefits and costs of individual loss terms across tasks?
Yes, each term moves the representations as intended. The trade-off arises because benign prompts close to the concept share much of its representation, so the terms that push the concept away also move them: the more these benign representations drift, the lower the attack success and the higher the NearConcept failure. We measured each term on Qwen-Image-2.1.
Table 2: Representation measurements on Qwen-Image-2.1
| term | measurement | CIRCE | comparison |
|---|---|---|---|
| rerouting | similarity to the original model's activations, target inputs | 0.54 | 0.84–0.86 output-level erasure |
| separation | cosine similarity between target and benign centroids (lower is more separated) | 0.74 ± 0.02 (n = 10) | 0.88–0.90 output-level erasure, 0.99 ESD + output anchor, 0.99 original model |
| clustering | spread of target activations | 0.23 | 0.30 without clustering |
CIRCE reroutes target representations far more than output-level erasure, separates target and benign centroids, and tightens the target cluster compared with training without clustering.
Within the 16 runs of CIRCE's family (full recipe and ablations), the drift of benign representations on NearConcept prompts predicts PAIR (Spearman ρ = −0.87) and NearConcept failure (ρ = +0.91). This also suggests when the trade-off applies: a term costs preservation where benign prompts lie close to the target in representation space, and costs little where they do not. The edit re-encodes the concept rather than removing it: a classifier retrained on each model still decodes the concept, with balanced accuracy 0.949 for CIRCE and 0.966 for the base model (figure).
Across tasks, clustering lowers attack success at matched image quality (W1), and its preservation cost depends on the task. On SD it costs nothing on NearConcept, with NearConcept failure between 0.21 and 0.29 for weights 0–1.0 (figure). On Qwen, within CIRCE's runs, tighter clustering goes with more NearConcept damage (ρ = −0.54, p = 0.035). On UnlearnCanvas, retention falls as the clustering weight rises (figure). Separation protects retention, and removing it lowers in-domain accuracy by 6.5 points on styles and 2.7 on objects on average (Table 11). In short, clustering buys robustness, at a preservation cost when nearby benign content moves with the concept, and separation limits that cost. We will include these measurements, the correlations and the effect of each term in the appendix.
W3 / Q3. Visual inversion (TINA / TINA+)
When access to reference images and initial latents is allowed, does CIRCE remain robust to visual-inversion recovery methods such as TINA/TINA+? If this access setting is outside the intended scope, please clarify the corresponding limits of the conclusions.
We thank the reviewer for this question, which led to a finding we found interesting.
TINA+ recovers the target from CIRCE in 57% of cases and from the undefended model in 64% (strict NudeNet), but it also "recovers" nudity from models whose denoiser was trained only on digits or fruit. We trained diffusion models in SD-1.4's latent space only on MNIST digits or only on photos of fruit. These models never generate nudity on their own (NudeNet flags 0/200 of the MNIST model's samples and 2/200 of the fruit model's). Yet TINA+ recovers nudity on 29% (MNIST) and 46% (fruit) of its 118 targets. A white-box attack with the budget of our other white-box attacks recovers nothing from either model (0/80). TINA+ also recovers nudity from every erasure method we tested, between 42% and 67% of targets for all 12 SD-1.4 baselines, so CIRCE (57%) is comparable to existing methods (for example ESD 53%, TRCE 57%, SafeGen 61% and STEREO 67%). The original TINA even succeeds on 57% of targets under strict NudeNet (81% under the lenient detector) with a UNet whose weights are all zero, and the TINA+ authors report that TINA succeeds on a randomly initialised UNet (their Table VII).
Given a reference image and its starting noise, these attacks can thus reproduce the image even from a denoiser that was never trained on the concept (figure). They might therefore measure how well an image can be inverted more than what the model still knows about the concept. We will add these results to the paper and state visual inversion as a limit of our conclusions.
W4 / Q4. SalUn c4 vs c5
The configuration search in Appendix A.1 selects SalUn c5, but the full benchmark comparison reports c4 without clearly explaining this choice.
Why does the full benchmark report SalUn c4 when c5 wins the configuration search? Can the full c5 results be provided, or can the specific reason for not evaluating or reporting them be explained?
The paper reported SalUn (unlearning restricted to salient weights) with c4 because the full c5 evaluation, which requires training and evaluating 70 models (50 styles and 20 objects), had not finished at submission time. We have now run it, and c4 has the higher mean of the six metrics on the full benchmark. The two configurations differ only in α (1.0 for c5, 0.2 for c4), and we will report both rows in the paper (figure).
Table 3: SalUn on the full UnlearnCanvas benchmark (UA: erasure, IRA / CRA: in- and cross-domain retention)
| style UA / IRA / CRA | object UA / IRA / CRA | mean of six metrics | |
|---|---|---|---|
| SalUn c4 (paper) | 74.8 / 98.1 / 66.7 | 82.4 / 99.1 / 84.4 | 84.25 |
| SalUn c5 | 45.6 / 99.2 / 81.3 | 63.9 / 99.3 / 95.9 | 80.87 |
c5 erases much less (style UA 45.6 vs 74.8) and led the search only on its 4-concept, 200-image subset.
We thank the reviewer again for their thoughtful review, which helped make our paper even better. If our responses address the reviewer's concerns, we would appreciate it if they would reconsider their score. We also invite the reviewer to respond, so that we can continue the exchange and further improve the quality of our paper.
We thank the reviewer for their comments. We are encouraged that they acknowledged our broad evaluation, including different adaptive attacks, loss ablations and the human evaluation. Throughout this response, we link figures in our anonymous GitHub repository that illustrate each finding. We invite the reviewer to look at them while they read our response. We will upload the updated paper PDF in the coming days.
W1 / Q1. Representation vs output supervision, controlled
On SD-1.4, erasing in representations rather than at the output gives about 3× lower attack success at the same NearConcept failure and higher MOS. On Qwen-Image-2.1, clustering, a representation-level term, also lowers attack success at matched image quality.
In our rebuttal, to separate where the supervision acts from everything else, we trained CIRCE with its losses moved to the output. In the output-level version, the same erasure losses act on the denoiser's prediction (averaged over image positions) instead of its internal activations, and the benign anchor keeps the prediction for benign prompts close to the original model's. We trained all four combinations of erasure location and anchor location. All of them update the same layers with the same LoRA rank, training data, timestep range and number of steps, so they differ only in where the losses act.
Table 1: Location of the losses on SD-1.4. Each cell gives PAIR (NearConcept failure, MOS), mean over runs.
At the same NearConcept failure and higher MOS, erasing in representations lowers PAIR from 0.23–0.25 to 0.075. Every representation-level run has lower PAIR than every output-level run, a difference of 0.16 (exact permutation test over the 4 and 8 runs, p = 0.004, the smallest p possible with this many runs) (figure).
On Qwen-Image-2.1 (10 seeds per cell), we compare at matched quality, because output-level erasure lowers PAIR partly by degrading the model. Moving only the erasure losses does not change PAIR, but the two other representation-level terms do: moving the benign anchor to representations lowers PAIR by 0.08 at matched MOS (p = 0.04), and clustering lowers it by 0.22 (p < 0.001, figure).
A standard output-level method confirms this: ESD with an output anchor, tuned over 47 runs, has 0.17 higher PAIR than CIRCE at matched NearConcept failure (p = 0.0004, figure). Across all 274 Qwen-Image-2.1 models we trained (83 CIRCE runs, 116 baseline runs and 75 controls), every output-level run with MOS above 4 is beaten by a CIRCE run with both lower PAIR and higher MOS (figure).
Representation-level erasure is more robust because it moves the concept's internal representation, which output-level training barely does: a probe trained on the original model still finds the concept in 96% of target inputs after ESD with an output anchor, and in 94% after output-level CIRCE, against 71% after CIRCE. An attacker therefore has less of the concept left to recover. This matches what circuit breakers found for LLMs, where rerouting representations gave more robustness than training on outputs alone (Zou et al., 2024). We will add this comparison to Sec. 4 and state that supervising representations moves the robustness–quality frontier.