- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper investigates the adversarial robustness of object detectors under transferable black-box attack settings. The authors argue that conventional per-image iterative optimization attacks tend to overfit the surrogate detector and suffer from limited cross-model transferability, primarily due to cross-detector gradient misalignment and inter-object gradient conflict within multi-object scenes. To address these issues, the authors propose DASH, shifting the attack paradigm from per-image pixel optimization to distribution-level adversarial distribution learning via an input-conditioned generative mapping . The method incorporates two core objectives: a class-agnostic confidence suppression loss to coordinate suppression across multiple objects and mitigate gradient conflict, and an object-region CLIP feature disruption loss to provide detector-external semantic supervision and reduce surrogate representation dependence. The framework is instantiated using a conditional GAN (DASH-GAN) and Stable Diffusion with LoRA (DASH-SD). Evaluated after training on VOC2012, experiments assess black-box transferability across 13 detectors on VOC2012, INRIA Person, and COCO-500, along with evaluations on generation efficiency, LPIPS perceptual quality, robustness against defended detectors, threshold sensitivity, and ablation studies.
Critical strengths
- Distribution-level transferable attack paradigm with empirical gains: Rather than optimizing perturbations per image independently, the paper trains a shared generator to learn a mapping from the natural to the adversarial distribution. In Table 4, under identical CA+CLIP objectives, black-box average ASR for per-image PGD is only 47.54% / 61.92%, whereas DASH-GAN achieves 85.21% / 86.24% with substantially lower variance across unseen victims. This supports the premise that distribution-level generative modeling can enhance black-box transferability.
- Extensive experimental evaluation: The evaluation spans three benchmarks (VOC2012, INRIA Person, COCO-500) across 13 victim detectors covering one-stage, two-stage, end-to-end, and Transformer-based architectures. The authors also report cross-dataset transfer, evaluation against defended detectors (ODDefense), runtime efficiency, LPIPS, threshold sensitivity, and loss ablations. At test time, DASH-GAN and DASH-SD require 0.02 s/image and 0.75 s/image respectively, eliminating per-image gradient optimization.
Critical weaknesses
- Severe issues with figures and AI use disclosure: Certain components of Figure 1 appear to be direct outputs from text-to-image generative models without manual curation. For instance, the detector diagram in "Transfer to unseen detectors" lacks coherent structural logic and exhibits blurred boundaries, while meaningless vertical artifacts appear in the "Surrogate gradient misalignment" plot. However, the AI Use Statement only claims verification of code, references, and manuscript text, completely omitting any review of figures. Furthermore, the loss notation in Figure 2 conflicts with or is undefined in the main text equations, and Figures 4 and 5 suffer from low resolution and distortion, hindering readability.
- Unclear origin of the spatial gate in DASH-SD and threat model inconsistency: Section 3.5 (page 6) defines as an "object-region gate obtained from clean image boxes." In a realistic black-box scenario, the attacker receives unlabeled input images. If is derived from ground-truth bounding boxes, this constitutes test-time ground-truth leakage. If is predicted by the surrogate detector, the surrogate must be queried during inference, contradicting the claim of "one-shot generation" without surrogate dependency at test time. Neither the main text nor Algorithm 1 clarifies how is obtained during inference, representing a major logical gap.
Questions for authors
- Source of the spatial gate during inference in DASH-SD: In Equation (10), the spatial mask modulating LoRA is defined as "obtained from clean image boxes." During black-box inference on unannotated images, how is acquired? Does this rely on ground-truth boxes? If it relies on predictions from the surrogate detector, does that mean the surrogate must be executed at test time, undermining the claim of one-shot generation without surrogate involvement? Please clarify the inference pipeline and threat model.
- Fairness of baseline comparisons and mixture of white-box/black-box evaluations: In Table 1, the reported DASH results are presented across three surrogate detectors and include white-box evaluations where surrogate and victim coincide, whereas baseline methods are reported with only a single column. Could the authors provide a strictly controlled black-box comparison matrix where surrogate detectors, iteration budgets, and evaluation protocols are fully aligned, as well as specify the iteration counts, step sizes, and random restarts used for iterative baselines such as DAG, TOG, and CAT?
- Generation provenance of Figure 1 and AI disclosure: Was Figure 1 generated using a text-to-image model? Why did the AI Use Statement omit the disclosure and verification of figures?
- Inconsistency between main and ablation metrics: Tables 1–5 report object-level ASR, whereas Table 7 switches to the stricter image-level ASR. What is the justification for switching metrics, and what are the corresponding results for baseline methods under the stricter image-level ASR standard?