- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes NDDL, a framework for backdoor prompt detection and trigger localization in text-to-image diffusion models. It extracts temporal representations and trains a lightweight, timestep-conditioned network on benign trajectories to predict next-step feature increments. During inference, prediction errors serve as anomaly scores for detection, while low-semantic token substitutions enable trigger localization. Experiments evaluate the framework across multiple diffusion architectures, attack methods, and trigger types.
Critical strengths
- The paper is clearly written and easy to follow.
- The evaluation covers a broad range of attacks, diffusion architectures, and trigger types, providing substantial empirical support for the method’s effectiveness in the evaluated settings.
Critical weaknesses
- Since the dynamics predictor is trained on benign trajectories, large prediction errors may reflect a shift in the benign input distribution rather than backdoor activation. The paper should evaluate benign OOD inputs: 1) training on benign DiffusionDB captions and testing on benign COCO captions, 2) training on benign prompts longer than 15 tokens and testing on prompts shorter than 7 tokens.
- Although a threshold formula is provided, the parameter values like are unclear, limiting reproducibility and practical deployment.
Questions for authors
The claim of “a new transition-dynamics perspective” appears overstated, as [1] already examines dynamic features for backdoor detection in T2I diffusion models. The authors should discuss this work and clarify the distinction between the two approaches, at least in the related work section.
[1] Wang et al. Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models. TPAMI’25.
7 comments
Response to Reviewer (part 2 of 3)
2. Response to Threshold Selection and Reproducibility
We thank the reviewer for pointing out the need to clarify the threshold configuration. We agree that providing explicit parameter settings is important for reproducibility.
In NDDL, the detection threshold is calibrated using only benign validation trajectories. Specifically, we fit a Gaussian distribution to their anomaly scores and determine the detection threshold as:
where and are estimated from benign validation scores, and is a balance weight ( in our experiments). Similarly, the localization threshold is determined using the same procedure as .
To improve reproducibility, we have added the detailed model and hyperparameter configurations in Appendix D.1 (Table 11), including the loss weights and detection/localization thresholds across different diffusion backbones. Table R3 presents the hyperparameter configurations of NDDL.
Table R3: Hyperparameter configurations of NDDL across different models.
| Backbone | |||||
|---|---|---|---|---|---|
| SD1.5 | 1.0 | 5.3 | 2.5 | 0.00179 | 0.00081 |
| SDXL | 1.5 | 5.0 | 2.5 | 0.00154 | 0.00076 |
| SD3.5 | 1.0 | 6.0 | 2.8 | 0.00213 | 0.00092 |
| PixArt-α | 1.3 | 5.7 | 2.2 | 0.00169 | 0.00079 |
Response to Reviewer (part 3 of 3)
3. Response to the Novelty Concern: Distinction from DAA
We thank the reviewer for highlighting the closely related work DAA. We acknowledge that DAA has already investigated the temporal evolution of attention representations for backdoor detection. However, the fundamental distinction between DAA and NDDL lies in what is modeled and how backdoor anomalies are identified.
Methodological Distinction. Specifically, the methodological differences can be summarized as follows:
- Modeling Objective: DAA characterizes attention evolution patterns to identify anomalous behaviors. In contrast, NDDL explicitly learns normal diffusion transition dynamics from benign trajectories, integrating attention, latent states, and noise predictions into a unified multi-space representation.
- Detection Criterion: NDDL employs a timestep-conditioned predictor to estimate normal transitions and identifies backdoor anomalies through inconsistencies between observed and predicted transitions, rather than relying solely on characteristics of attention evolution.
Experimental Comparison. To further substantiate this distinction, we have included DAA-I and DAA-S as additional baselines across four diffusion models.
Table R4: Detection comparison with DAA across different diffusion models.
| Backbone | Method | ACC ↑ | AUROC ↑ |
|---|---|---|---|
| SD1.5 | DAA-I | 76.0 | 75.9 |
| DAA-S | 78.1 | 78.6 | |
| NDDL (Ours) | 98.1 | 98.2 | |
| SDXL | DAA-I | 77.5 | 77.1 |
| DAA-S | 79.8 | 80.4 | |
| NDDL (Ours) | 98.0 | 98.0 | |
| SD3.5 | DAA-I | 71.5 | 71.6 |
| DAA-S | 75.8 | 75.7 | |
| NDDL (Ours) | 91.2 | 92.7 | |
| PixArt-α | DAA-I | 76.4 | 77.0 |
| DAA-S | 86.5 | 85.6 | |
| NDDL (Ours) | 92.3 | 91.7 |
Results on SD1.5 and SDXL are averaged across five attacks; those on SD3.5 and PixArt-α correspond to Rickrolling.
The comparison highlights two aspects of NDDL's effectiveness:
- Detection Performance: As shown in Table R4, NDDL consistently outperforms both DAA variants in ACC and AUROC across all four evaluated diffusion backbones. Specifically, NDDL improves the average AUROC by 22.32 and 19.62 percentage points on SD1.5, and 20.94 and 17.64 percentage points on SDXL, compared with DAA-I and DAA-S, respectively. These improvements are also observed on the evaluated DiT-based architectures.
- Trigger Token Localization: Beyond the detection results in Table R4, NDDL additionally supports explicit trigger token localization, with localization performance reported separately in Tables 2, 3, 13 and 14 of the revised manuscript. In contrast, DAA-I and DAA-S do not provide dedicated mechanisms for identifying malicious trigger tokens.
Experimental Evidence for Normal Dynamics Learning. We further investigate whether learning normal transition dynamics contributes to detection performance, beyond directly exploiting temporal differences.
Table R5: Ablation study of normal dynamics modeling on BadT2I (%).
| Modeling Strategy | ACC ↑ | AUROC ↑ |
|---|---|---|
| Raw Diff | 30.5 | 32.9 |
| Linear w/o Time | 42.8 | 43.2 |
| Linear w/ Time | 38.7 | 36.8 |
| NDDL w/o Time | 62.2 | 60.5 |
| NDDL (Ours) | 99.0 | 99.2 |
The ablation results provide two important observations:
- Normal Dynamics Modeling: Directly using raw transition differences or linear predictors yields limited detection performance. In contrast, learning nonlinear normal transition dynamics substantially improves detection effectiveness, supporting the importance of explicitly modeling benign diffusion evolution.
- Timestep Conditioning: Incorporating timestep information further improves the effectiveness of normal dynamics learning, increasing AUROC from 60.5% to 99.2%. Similar improvements are observed across the other four attacks (Appendix D.7, Table 17).
Together, these results provide empirical evidence that NDDL's effectiveness stems from learning timestep-conditioned normal diffusion transition dynamics, rather than merely exploiting temporal attention information. We have also expanded the Related Work discussion to clarify the methodological distinction between NDDL and DAA in the revised manuscript.
We sincerely thank the reviewer for the thoughtful comments and valuable suggestions, which have helped us strengthen the evaluation of generalizability and clarify the experimental configurations. We hope that the additional results and revisions adequately address the reviewer's concerns.
Response to Reviewer (part 1 of 3)
1. Response to Robustness to Benign Distribution Shifts
We thank the reviewer for the constructive comments and positive assessment of our work. We appreciate the concern that a normal dynamics model trained exclusively on benign samples may mistake distributional variations in legitimate prompts for backdoor-induced anomalies. To address this issue, we have conducted additional experiments under two types of benign prompt distribution shifts:
We report the false positive rate (FPR) and true positive rate (TPR) to evaluate whether these shifts lead to false alarms or degraded backdoor detection.
Table R1: Robustness to benign prompt distribution shifts on SD1.5 (%).
Results are averaged across five backdoor attacks: BadT2I, EvilEdit, MasqLoRA, Rickrolling, and STEBA.
As shown in Table R1, NDDL maintains relatively stable detection performance under both distribution shifts:
We further conduct experiments on SD3.5, a DiT-based diffusion model. The results are summarized below.
Table R2: Robustness to benign prompt distribution shifts on SD3.5 (%).
As shown in Table R2, NDDL still maintains comparable FPR and TPR under both distribution shifts on SD3.5. In particular, the cross-dataset shift decreases TPR by only 1.2 percentage points, while the prompt-length shift decreases TPR by 0.4 percentage points.
Overall, these experiments provide empirical evidence that NDDL can tolerate the evaluated benign distribution shifts across both UNet- and DiT-based diffusion architectures. We have included the detailed results in Table 4 and Appendix D.5 (Table 15) of the revised manuscript.