- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates the adversarial robustness of feed-forward 3D Gaussian Splatting (3DGS) models and proposes AdvSplat, a black-box attack framework. It uses low-frequency DCT perturbations to reduce the search dimensionality, combined with either NES-based gradient estimation or gradient-free CMA-ES optimization to generate adversarial examples. Experiments show that small input perturbations can substantially degrade novel-view reconstruction quality.
Critical strengths
- The work addresses adversarial security in feed-forward 3DGS, a problem with practical relevance.
- The method is straightforward, using low-frequency perturbations to reduce the search dimensionality while covering two black-box optimization approaches.
- The attack effects are substantial: reconstruction quality degrades markedly across three models and two datasets. DCT control experiments further validate the role of frequency-domain search.
Critical weaknesses
- The core design mainly combines low-frequency DCT perturbations with established NES and CMA-ES algorithms, without a clearly distinctive attack mechanism tailored to 3DGS. It is unclear whether the work offers a unique task-specific motivation or insight.
- The main experiments primarily compare performance before and after attacks, without comparisons against existing black-box attacks under the same query budget. This makes it difficult to assess the method's competitiveness.
- Although the paper emphasizes query efficiency, the experiments involve numerous iterations and candidate samples. The actual query cost and efficiency gains over existing methods are not explicitly reported.
- For pose-free models, drift in pose estimation may affect rendering metrics. The paper does not adequately distinguish geometric reconstruction errors from quality degradation caused by viewpoint shifts.
Questions for authors
- What new technical designs does this work introduce beyond directly combining DCT with standard NES/CMA-ES?
- Could the authors provide comparisons with existing black-box attacks under identical query budgets?
- For pose-free models, can the authors distinguish pose drift from actual geometric reconstruction errors?