- Rating
- 3
- Confidence
- 2(−1)
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes ADVO, a transferable image-protection framework designed to prevent unauthorized exploitation of images by closed-source multimodal systems without requiring access to the target models. The key idea is to combine two complementary protection mechanisms: refusal induction, which encourages a target system to reject a protected image, and source-semantic disruption, which degrades the source-image representation when the system continues processing the image. ADVO uses a two-stage framework based on heterogeneous open-source proxy encoders. In the first stage, it constructs encoder-specific refusal prototype banks from benign and policy-violating reference images by removing dominant benign feature directions and selecting representative policy-sensitive features. In the second stage, it optimizes a bounded perturbation for each image, assigning refusal induction to low-saliency regions and source-semantic disruption to high-saliency regions, while also using concealment regularization and adaptive proxy weighting to improve transferability and visual concealment. The method is evaluated primarily on image description across six closed-source multimodal systems, where it achieves an average protection success rate of 89.2%, outperforming the strongest evaluated baseline. The authors also provide ablations supporting the main design choices, robustness evaluations under common image transformations, and qualitative results showing that the same protected images can hinder downstream image editing and imitation.
Critical strengths
- The paper introduces a well-motivated dual-mechanism protection strategy for heterogeneous closed-source multimodal systems. Rather than relying solely on transferable feature disruption or refusal induction, ADVO combines refusal induction with source-semantic disruption, so protection can remain effective even when refusal behavior does not transfer. This is particularly consequential in the closed-source setting, where target architectures and safety mechanisms are inaccessible and can differ substantially across systems. The results on Grok 4.6 are especially supportive of this design: despite a refusal rate of only 5.6%, ADVO still achieves an 84.5% protection success rate, suggesting that semantic disruption provides a meaningful fallback when refusal induction is ineffective.
- The empirical validation is strong and generally supports the main design choices. ADVO achieves the best protection success rate across all six evaluated closed-source systems, with an average PSR of 89.2% compared with 69.1% for the strongest evaluated baseline. The ablation studies further show substantial degradation when removing either refusal induction or source-semantic disruption, replacing the prototype bank with a single reference, removing saliency-guided region allocation, or fixing prototype targets. Together, these results provide convincing evidence that the observed gains are not attributable to a single incidental component, but arise from the proposed combination of transferable refusal features, semantic disruption, and multi-proxy optimization.
Critical weaknesses
- The main protection metric does not fully establish that the image is no longer exploitable. The primary quantitative evaluation defines a request as successfully protected if the target refuses or if the semantic similarity between the protected-image response and the clean-image response falls below a threshold. However, a low response similarity does not necessarily imply that important exploitable information—such as object identity, subject attributes, style, or other source-specific content—has been removed. As a result, the reported PSR may overestimate the extent to which the protected image is genuinely unusable for downstream exploitation. Additional task-specific or human-evaluated measures of retained source information would substantially strengthen the central claim.
- The evidence for robustness beyond image description is still limited. The strongest quantitative evaluation is concentrated on image description, while the editing and imitation experiments are primarily qualitative. In addition, the robustness study shows noticeable degradation under stronger preprocessing, particularly Gaussian blur, and the paper does not evaluate a stronger adaptive adversary that deliberately applies denoising or purification to remove the perturbation. Since the paper motivates ADVO as a general protection mechanism against closed-source image exploitation, stronger quantitative validation on downstream tasks and against adaptive preprocessing would be important for establishing the breadth and practical robustness of the claim.
Questions for authors
- How well does the current PSR metric correspond to actual loss of exploitable source information? The evaluation counts a sample as successfully protected when the target refuses or when the semantic similarity to the clean-image response is below 0.5. Could the authors provide evidence that this threshold correlates with failure to recover important source information, e.g., through human evaluation or additional task-specific measures of object/subject identity, attributes, retrieval, or style information? In particular, are there cases where the response similarity falls below 0.5 while the model still correctly recovers the key exploitable content of the image? This would materially affect how I interpret the reported 89.2% average PSR.
- How robust is ADVO to an adaptive adversary that deliberately attempts to remove the perturbation before querying the target system? The current robustness experiments cover JPEG compression, resizing, cropping, and Gaussian blur, and performance decreases under stronger blur. Have the authors evaluated stronger denoising, purification, re-rendering, or other preprocessing specifically chosen to suppress adversarial perturbations? Relatedly, can the authors provide quantitative evaluation for editing or imitation under such preprocessing, rather than only qualitative examples? Stronger evidence here would materially affect my assessment of the method’s practical robustness and the breadth of the claimed protection against image exploitation.
3 comments
Response to Reviewer 6Tig (2/2)
W2 and Q2. Adaptive Preprocessing
Common image transformations retain substantial protection, while targeted purification substantially weakens it. With JPEG compression at Q75, description PSR remains 88.6% on Gemini 3.8 and 86.9% on Qwen 3; the corresponding original results are 92.4% and 93.8%.
We additionally evaluate NAFNet denoising, Stable Diffusion VAE re-rendering, and diffusion purification. Under diffusion purification, PSR decreases to 57.8% on Gemini and 38.1% on Qwen 3. Table R3 reports both common and adaptive preprocessing. These results quantify a clear robustness limit under strong purification; the ability of purified images to preserve source fidelity requires separate image-quality assessment.
Q2. Editing and Imitation under Preprocessing
The same protected images are reused for editing and imitation without re-optimization. Their original total protection rates are 92.1% and 91.5%, respectively. After diffusion purification, these decrease to 45.6% and 45.3%. JPEG Q75 retains 88.3% and 87.8%, while learned denoising retains 68.0% and 67.5% (Table R4).
Table R3. Image-Description Protection under Common and Adaptive Preprocessing
| Category | Method | Gemini PSR ↑ | Qwen 3 PSR ↑ |
|---|---|---|---|
| Baseline | None (Original) | 92.4 | 93.8 |
| Common | JPEG (Q=75) | 88.6 | 86.9 |
| Common | Resize (256) | 89.2 | 81.2 |
| Common | Crop (75%) | 88.2 | 84.1 |
| Common | Blur (σ=1.0) | 83.4 | 76.3 |
| Adaptive | Learned Denoising | 72.1 | 56.0 |
| Adaptive | Image Re-rendering | 66.3 | 47.5 |
| Adaptive | Diffusion Purification | 57.8 | 38.1 |
PSR results are for Gemini 3.8 and the locally evaluated open-source Qwen 3 model.
Table R4. Editing and Imitation Protection under Preprocessing
| Category | Preprocessing | Editing protection (%) | Imitation protection (%) |
|---|---|---|---|
| Baseline | None (Original) | 92.1 | 91.5 |
| Common | JPEG (Q=75) | 88.3 | 87.8 |
| Common | Resize (256) | 88.9 | 88.3 |
| Common | Crop (75%) | 88.0 | 87.4 |
| Common | Blur (σ=1.0) | 83.3 | 82.6 |
| Adaptive | Learned Denoising | 68.0 | 67.5 |
| Adaptive | Image Re-rendering | 57.6 | 57.3 |
| Adaptive | Diffusion Purification | 45.6 | 45.3 |
Each task aggregates eight evaluated systems, with 100 valid samples per system. This table reports protected-input task failures, including refusal/blocking where present.
Thanks for the detailed response, which has addressed most of my concerns. I hope the authors can include more concrete examples or experiments involving denoising or other preprocessing methods in the future. I will maintain my current score.
Response to Reviewer 6Tig (1/2)
We thank the reviewer for recognizing ADVO's dual-mechanism design and cross-model results, and for the suggestions on metric validity and adaptive preprocessing. Supporting Tables are provided at the end of each response.
W1 and Q1. PSR and Source-Information Recovery
We conducted an independent human evaluation of 200 samples to assess whether PSR accurately reflects source-information protection. At the similarity threshold of 0.5, PSR reaches 91.5% on this subset, compared with a 90.0% human-verified protection rate. As shown in Table R1, human evaluation confirms 177 of 183 PSR-positive cases (96.7%), while identifying 6 cases where key source information remains recoverable despite being classified as protected. Conversely, 3 cases are judged protected by humans but missed by PSR. Overall, PSR agrees with human judgments in 95.5% of cases, supporting its reliability as a practical protection metric while revealing a small number of misclassifications.
We additionally report threshold sensitivity in Table R2. PSR ranges from 78.2% to 94.6% as the similarity threshold varies from 0.3 to 0.7, with 89.2% at the default threshold of 0.5 on the full evaluation set.
Appendix: Validation and Robustness Results
Table R1. Human Verification of PSR on 200 Samples
Human judgments assess whether key source information remains recoverable from model responses. PSR achieves 96.7% precision among cases classified as protected, with 95.5% overall agreement with human judgments.
Table R2. PSR Sensitivity to Similarity Threshold
Table R1 reports an independently verified 200-sample subset, whereas Table R2 reports threshold sensitivity on the full evaluation set.