- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper proposes SOSA-Attack, a targeted transferable attack against closed source MLLMs. Building on FOA-Attack, it constructs global and local representation sets with random image transformations. It computes uncentered moments of order two after scaling by the trace, then obtains subspace descriptors with a MaxExp spectral map. SOSA-Attack aligns structure of order two at both the image and patch levels between adversarial and target images. It also gradually combines the gradient from this alignment with the original gradient for first order feature alignment. The theory proves that, for empirical distributions induced by feature vectors scaled by the trace, the squared Frobenius norm of the difference between moments of order two is exactly equal to MMD with a polynomial kernel of degree two. It also gives upper and lower bounds relating the MaxExp subspace difference to this MMD. The experiments cover image captioning, VQA, and image classification. They test several closed source models, open source models, and MLLMs with enhanced reasoning.
Critical strengths
-
The paper combines descriptors of global and local representations of order two with the existing objective for first order feature alignment. Norm balancing and gradual gradient fusion give the method one optimization procedure. The design is fairly complete.
-
The paper evaluates image captioning, VQA, and image classification. It covers closed source models, open source models, and models with enhanced reasoning. The empirical analysis of cross model vulnerabilities in MLLMs has some value.
Critical weaknesses
-
Appendix D.3 says that each sample is first attacked with , and the victim model is queried. If the attack fails, the authors run it again with and keep the better result from the two runs. This creates an adaptive choice between two attempts based on feedback from the victim model. It may depart from a transfer attack that relies only on a surrogate model, and it can raise the final ASR. The paper does not report the actual average number of queries per sample or the total query budget. It also does not state whether all baselines use exactly the same query and optimization procedure. If this procedure is used for attack generation and result selection, the method should be explicitly described as a query-assisted adaptive black-box attack rather than a purely surrogate-model-based transfer attack.
-
The paper does not report results for clean images, repeated experiments, confidence intervals, or tests of statistical significance. It also does not evaluate all baselines on the same complete set of 1000 samples. The theory establishes only that the difference between moments of order two has an exact relation to MMD with a polynomial kernel of degree two. This result does not guarantee transferability to a black box model. Although w/o MaxExp and FOA-Attack offer partial comparisons, the paper does not include comparisons under the same budget and implementation framework for raw moments of order two, CORAL, or a polynomial kernel of degree two. It also does not directly compare using only the second order branch of SOSA-Attack with using only the first order branch of FOA-Attack. If the procedure from to , or the extra random views, is not matched for every baseline, the reported gains may partly come from extra attack attempts or extra computation. The experiments then do not establish that the gain comes from SOSA-Attack’s second order structure.
Questions for authors
-
Please state how many queries to the victim model each sample actually requires in Appendix D.3. State whether the decision to move from to uses the victim model’s actual output. Report separate results for fixed , fixed , and the adaptive setting. Also state whether all baselines use the same number of queries, optimization iterations, and computational budget. If feedback from the victim model enters the attack or the choice of the final result, please define the setting as an adaptive black box attack that uses queries.
-
The paper says that some earlier baselines are evaluated only on the first 100 samples, while recent baselines use all 1000 samples. Please evaluate every method on the same complete set of 1000 samples. Report results on clean images, repeated runs with multiple random seeds, confidence intervals, and tests of statistical significance. For GPT-4o scores, state the exact model version, temperature, decoding settings, control of randomness, and score calibration procedure.
-
The main text explicitly says that the method uses uncentered moments of order two. Please confirm that the implementation follows this definition. State whether any extra feature normalization is applied before constructing the moments and give the exact value of . Although w/o MaxExp and FOA-Attack offer partial comparisons, please also report comparisons under the same budget and implementation framework for raw moments of order two, CORAL, and a polynomial kernel of degree two. Include a direct comparison between using only the second order branch of SOSA-Attack and using only the first order branch of FOA-Attack. Please report the numbers of forward and backward passes, GPU memory usage, runtime, and API query cost for SOSA-Attack and each baseline.
2 comments
Thank you for the response and the added experiments. The fixed Kc=3 results and the new structural ablations addressed part of my soundness concerns, so I raised soundness, but I am keeping my rating. In the main tables, you still need to separate single query transfer from the adaptive Kc=3 to Kc=5 retry that uses victim feedback. The rebuttal also leaves out repeated runs with significance tests and omits the second order only ablation row from the table, while SOSA adds extra memory and runtime cost over FOA.
Thank you for your valuable review and suggestions. Below we respond to the comments in Weaknesses (W) and Questions (Q).
W1 / Q1. Victim feedback and query budget.
Thank you for asking where victim feedback enters the evaluation. SOSA-attack generate candidates using three CLIP surrogates with zero victim queries. At fixed Kc=3 or 5, each method submits one candidate per image to each victim. Appendix D.3 uses the same retry rule for both methods. We score the victim's actual output on the Kc=3 candidate and submit the precomputed Kc=5 candidate only if the first attempt fails. For N images and F first-attempt failures, each victim receives N+F candidate queries, averaging 1+F/N per image. These counts exclude reference and judge calls.
The table reports mean ASR (%) and queries per image across six non-thinking models on 1,000 pairs, with FOA listed first and SOSA second in each cell. With one query per image at fixed Kc=3, SOSA exceeded FOA by 15.1 percentage points on captioning, 5.2 on VQA and 11.9 on classification. Allowing a retry increased ASR for both methods. Because SOSA succeeded more often on the first submission, it required fewer retries on all three tasks. We also evaluated fixed Kc=5 with one query per image on a separate 100-pair captioning comparison. FOA / SOSA achieved 42% / 53% ASR on GPT-5.4 and 58% / 74% on Claude Opus 4.6.
W2 / Q2. Baseline coverage, uncertainty and caption scoring.
Thank you for asking why sample sizes differ. Using the first 100 source–target pairs gave all four earlier baselines identical images and targets. In captioning, AttackVLM, AdvDiffVLM and AnyAttack achieved at most 1% ASR on each of the six closed-source models, and SSA-CWA achieved 1–12% (Table 1). Given these results, we expected the gap to recent methods to persist and stopped those runs at 100 pairs. We evaluated SOSA and its closest baselines (FOA, M-Attack and M-Attack-V2) on all 1,000 pairs.
For clean source images, we used the same caption prompt, target references and scoring threshold. Clean success was 0.1% on Gemini 2.5 Flash and Claude Sonnet 4.6 and 0.0% on the other four models. Mean similarity ranged from 0.009 to 0.014. We used the
gpt-4o-2024-11-20with the Appendix D.1 scoring prompt, temperature 0 andmax_tokens=100. We adopted M-Attack's threshold (score ≥0.5) without separate human calibration.W2 / Q3. Second moments, ablations and computational cost.
Thank you for asking what the structural loss measures and how the two branches compare. We apply row-wise ℓ2 normalization, compute M=F⊤F/n without centering, and divide by tr(M)+ν, with ν=10−5. For the trace-scaled moments A,B, Eq. (14) uses the identity of Li et al. [1].
D=∥A−B∥F2=MMDk2,k(u,v)=(u⊤v)2.
We prove the MaxExp bound in Eq. (15).
LS=∥Ψρ(A)−Ψρ(B)∥F2,γ2D≤LS≤ρ2D.
Eq. (15) gives D≤LS/γ2 on the surrogate. We will revise Sec. 4.3 to clarify this implication. We evaluate transfer empirically through victim ASR.
All ablations used the first 100 captioning pairs, fixed Kc=3, 300 steps and one submission per image per victim. The three structural controls retained the first-order term. After increasing the view count of FOA to 20, both ASR metrics improved. At 20 views, full SOSA exceeded FOA by a further 10 and 9 points.
In separate timing runs on 100 captioning pairs, SOSA took 1.40–1.48 times as long as FOA at fixed Kc. Peak GPU memory was 7.79 GiB for FOA, 17.87 for 20-view FOA, 18.32 for the kernel control and 17.90 for the other variants. Feature inputs / gradient calls totaled 270,000 / 30,000 for FOA, 1,806,000 / 90,000 for second-order only and 1,476,000 / 90,000 for each remaining variant. These count individual image inputs and
torch.autograd.gradcalls. Batched forward-call totals and comparable compute records for earlier baselines are unavailable.References
[1] Y. Li, N. Wang, J. Liu and X. Hou. Demystifying Neural Style Transfer. IJCAI 2017, pp. 2230–2236.