- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
To address the identified challenges of modality imbalance, angular imbalance, and digital-to-physical transfer gap, this paper propose three key techniques: (1) an adversarial shape-texture co-optimization (STCO) method that balances attack effectiveness across both modalities; (2) an angle-adaptive attack strategy (AAAS) that allocates more optimization effort to hard-to-attack viewpoints; and (3) a cross-modal foreground and background Expectation over Transformation (CFBE) method that enhances physical-world transferability. Extensive experiments in both digital and physical worlds, demonstrate the effectiveness of our attack against the state-of-the- art RGB-T detector and its strong transferability to unseen detectors.
Critical strengths
- The authors conducted extensive experiments, effectively demonstrating the validity of the proposed scheme.
- The full-view attack proposed by the authors is a significant issue.
Critical weaknesses
- This framework primarily combines various techniques explored in previous research on adversarial attacks. Although integrating these components into RGB-T attacks is reasonable, the paper does not sufficiently demonstrate the novelty of their approach.
- The paper does not clearly establish whether the baseline attacks are evaluated under comparable conditions in terms of the number of stickers, surface coverage, and full-view optimization budget. This makes it difficult to determine whether the reported improvements arise from the proposed techniques or differences in experimental configurations.
- The physical experiments are conducted on 1:24 scale model vehicles under controlled conditions. It remains unclear whether the proposed adversarial patterns can maintain their effectiveness on full-size vehicles and across different physical environments.
- The paper primarily reports average ASR across different viewing angles, without providing worst-viewpoint or lower-percentile ASR.
Questions for authors
- Can the authors provide comparisons in which the baseline attacks are optimized using the same number of stickers, surface coverage, and full-view optimization budget as the proposed method?
- How well do the attack patterns generalize to full-size vehicles and different physical environments?
- Can the authors report worst-viewpoint or lower-percentile ASR to demonstrate whether the proposed method consistently improves attack effectiveness at difficult viewing angles?