- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Adversarial Scenario Attack (ASA), a score-based black-box attack that generates natural adversarial examples by searching over natural-language editing scenarios rather than pixel-level perturbations. ASA uses an MLLM to propose edits in three categories—background, weather/atmosphere, and material/color—and applies them with a text-guided image editor. Victim-model feedback is used to iteratively refine the scenarios, while a Greedy Explorer combines complementary edits. The method achieves strong attack success under a 100-query budget.
Critical strengths
-
ASA achieves high ASR across diverse architectures, including CNNs, Transformers, SSMs, robust models, and VLMs, while using relatively few victim-model queries.
-
The attack outputs are interpretable and natural-looking.
-
Some class-neutral scenarios remain effective across many ImageNet classes and multiple model families, suggesting that these models may share common vulnerabilities to certain natural scene changes.
Critical weaknesses
-
The high-level idea of moving from pixel-level perturbations to natural-language-controlled semantic or scenario-level modifications does not seem fundamentally new. Prior work [a] has already explored generating natural adversarial examples by manipulating human-interpretable attributes through text prompts. ASA follows a similar formulation, with the main additions being victim-model feedback and MLLM-based iterative refinement of the editing scenarios. Therefore, I would view ASA more as an automated, closed-loop extension of existing semantic-prompt attacks rather than a fundamentally new attack paradigm.
-
A fairer comparison with query-based unrestricted attacks is needed to show that the gain really comes from ASA rather than its much larger perturbation space.
-
In the human study, only 75.4% of judgments considered the edited object to still be the same as the original one. This means a non-trivial fraction of “successful attacks” may simply change the image too much, which weakens the validity of the reported ASR as natural adversarial examples. The human study is also only conducted on ResNet-50 examples.
-
“Query-efficient” does not necessarily mean computationally efficient. ASA reduces victim-model queries, but each candidate still requires MLLM inference and large-scale image editing. The appendix shows that ASA has a higher per-image generation cost and a higher total runtime than AdvFlow, DifAttack, and CGAttack. Therefore, the efficiency claim should be understood mainly as query efficiency, not end-to-end efficiency.
-
ASA assumes access to the ground-truth label and confidence scores from the victim model. In many real black-box APIs, only the top-1 prediction may be available. For MLLM victims, the method even relies on self-reported confidence values, which the paper acknowledges are neither internal logits nor calibrated probabilities. This limits the practical generality of the attack setting.
[a] Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models, CVPR 2024
Questions for authors
see Weaknesses
3 comments
W3. Human study.
We ran a new, larger human study with the majority-vote rule of [b]: a majority of seven raters judged 84.4% of all ASA successes on ResNet-50 (740/877), and 88% of a 100-image Swin-B sample, to be natural-looking and to show the original class.
Protocol.
- Raters and images. Seven non-author participants each rated all 877 ASA images that fool ResNet-50 on NIPS 2017.
- Presentation. One image at a time, without the original and without being told that the images were edited. Image order and the order of the two class labels in Q2 were randomized per participant.
- Q1. "Does this image look like a natural photograph of a real scene?" (yes/no).
- Q2. "Which label best describes the main object?" (original class, post-attack class, or "unsure").
The two questions are the two conditions of our definition of natural (Sec. 3): a scene that could occur in the real world, whose main object still belongs to the original class.
ResNet-50. By per-image majority (at least 4 of 7 raters), 97.3% were judged natural, 86.9% were assigned the original class, and 84.4% satisfied both.
Swin-B. The same participants rated 100 Swin-B adversarial images, with originals drawn at random from those on which ASA fooled both victims. 88% satisfied both criteria versus 81% for the ResNet-50 images of the same originals (paired difference +7.0 pp, 95% CI −2.0 to +16.0): on the same originals, the rate is not lower on a second architecture.
Effect on Tab. 1. We multiplied ASA's ASR on every victim by the ResNet-50 rate (740/877) and left every baseline undiscounted. ASA still ranks first:
- vs. the unrestricted baselines ($\epsilon = 255/255$, W2): on all ten victims, by 49 pp on average (73.6% vs. 24.3%) and by at least 31 pp on every victim.
- vs. the $\epsilon = 12/255$ baselines: on nine of ten victims, by 30 pp on average (73.6% vs. 43.4%).
| RN-50 | ConvNeXt | Swin | DeiT | ViM | MambaVision | Adv-Res | Adv-Inc | CLIP | SigLIP2 | Mean | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Best baseline, $\epsilon = 12/255$ (Tab. 1) | 82.62 | 49.39 | 23.93 | 26.59 | 32.12 | 20.85 | 44.30 | 52.78 | 57.20 | 43.89 | 43.37 |
| Best baseline, $\epsilon = 255/255$ (W2) | 30.47 | 24.64 | 25.91 | 20.55 | 20.24 | 19.29 | 23.96 | 28.12 | 25.32 | 24.91 | 24.34 |
| ASA $\times$ ResNet-50 human-verified rate | 79.40 | 73.59 | 75.38 | 74.28 | 76.70 | 65.73 | 80.89 | 82.43 | 71.04 | 56.68 | 73.61 |
ASR (%). Last row: ASA's ASR × 740/877. Bold: highest in each column.
We have added the study to Sec. 4.6, the Swin-B results to App. O, and the table above to App. M.
[b] Constructing Unrestricted Adversarial Examples with Generative Models. NeurIPS 2018.
W4. Computational efficiency.
Our efficiency claim concerns queries, and the revision states this explicitly (App. D). The per-image time during the search (25.98 s, Tab. 14) is that of an off-the-shelf MLLM and image editor generating a scene-level change, and App. D lists it as a limitation for large-scale evaluation. In runtime, ASA also has advantages in three respects:
- No attack-specific training. ASA requires none; the baselines need 651.6–69,343.2 s before generating (Tab. 14).
- Lower total runtime at small scale. Because the baselines pay this cost up front, ASA's total runtime is below that of AdvFlow, DifAttack, CGAttack, and MCGAttack up to about 25, 190, 620, and 2,790 images, respectively (from Tab. 14).
- Fast reuse. In the prompt-level transferability test (Sec. 4.3), scenarios found in the RN-50 search are applied to new images without search, at about 0.7 s per image, within the baselines' range. The three most frequent ones still reach 20.75–34.62% ASR over all 1,000 classes and 13 models (Tab. 3).
W5. Threat model
Ground-truth label. ASA makes the same label assumption as the baselines we compare with, and the assumption is removable. Wherever $y$ is used (Sec. 3.1–3.2), it can be replaced by the victim's prediction on the clean image, which equals $y$ on the clean-correct samples we evaluate and costs one extra query.
Confidence scores: classifiers. ASA is a score-based attack (Sec. 3.1), and score access is available in practice: commercial classifier APIs such as Google Cloud Vision return confidence scores, and score-based attacks have been demonstrated on them [c].
Confidence scores: MLLMs. On MLLM victims, ASA needs no provider-released scores. The victim is asked in text for its confidences, which are neither logits nor calibrated probabilities, and these suffice. We ran the protocol of App. J (100 clean-correct NIPS 2017 images, 100 queries) on the closed-source gpt-6-luna:
| Victim | ASR (%) | Avg. Q |
|---|---|---|
| Gemma-4-E4B | 76.0 | 11.14 |
| Qwen3-VL-4B-Instruct | 83.0 | 8.71 |
| gpt-6-luna (closed-source, new) | 78.0 | 12.53 |
Avg. Q: attack queries per successful image.
We have added this result to Sec. 4.7 (details in App. J).
[c] BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack. ICLR 2024.
We thank the reviewer for the constructive review. We address each point below. All table, figure, section, and appendix numbers refer to the revised version.
W1. Relation to [a].
ASA's contribution is a structured search over natural-language edits of a source image, proposed by an MLLM. It has two components:
Victim score feedback and MLLM-based iterative refinement alone do not account for ASA's gains. ASA w/o S,G keeps both, with the same MLLM, image editor, and 100-query budget, and removes only S and G. It falls 37.7–53.6 pp below ASA across the four victims (largest on ConvNeXt: 33.6% vs. 87.2%; Fig. 4). Removing G alone (ASA w/o G) costs 7.7–16.6 pp.
ASA does not follow [a]'s formulation. The two differ in four respects:
We have added [a] to the related work (Sec. 2.1).
[a] Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models, CVPR 2024
W2. A comparison with query-based unrestricted attacks.
ASA is not strong merely because it is unbounded: it attacks along a different axis, images of scenes that could occur in the real world (our definition of natural, Sec. 3). Two comparisons in this unrestricted setting support this. Since, to our knowledge, no score-based query attack is unrestricted, we removed the bound from the Table 1 baselines, and ASA leads them by at least 42 pp (a). ASA's own ablation is a second unrestricted attack, and it falls at least 37 pp short of ASA (b).
(a) The Table 1 baselines with the bound removed (new). We re-ran all four baselines under the following setting:
Every baseline flips the label on 83.9–100% of the images, but the verifier rejects more than 99% of the candidates it checks. Without the bound, pixel-space attacks can therefore change the label, but not with images that could occur in the real world: enlarging $\epsilon$ does not reach this axis.
(b) An unrestricted attack built from ASA's components. ASA w/o S,G (Sec. 4.8, Fig. 4; see W1) differs from ASA only in lacking scenario competition (S) and greedy composition (G), so it is unrestricted in the same way. It falls 37.7–53.6 pp short of ASA across the four victims of Fig. 4.
We have added (a) to Tab. 1, Fig. 3(b), and Sec. 4.2.1, with full results in App. L.