仅用一个源模型实现高效可迁移的语义分割攻击
IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks
- 将攻击过程设计为可微分的链式计算，共享梯度提升效率
- 在Pascal VOC和Cityscapes上达到与单源基线相当的迁移性
- 比多模型集成攻击更快，适合资源受限场景
语义分割模型易受可迁移对抗扰动影响，但评估密集预测模型的迁移攻击计算成本较高。现有集成攻击通常依赖多个代理模型，增加计算开销，尤其对分割任务更难。本文提出一种高效的单源替代方案，将可迁移攻击构造为不同可微攻击组件的链式计算，使昂贵的源模型梯度计算得以共享。为缓解链式组合引入的更新不稳定性，进一步采用类似积分梯度的路径平均方向作为经验稳定化启发式。在Pascal VOC和Cityscapes数据集上，评估了基于CNN和Transformer的分割模型间的迁移效率权衡。IGME在仅访问一个源模型的前提下，相比单源基线具备竞争力的迁移性，且运行时间显著优于模型集成攻击。
原文摘要 · Abstract (English)
Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be computationally expensive. Existing ensemble attacks often rely on multiple surrogate models, increasing the computation cost, even harder for segmentation. This paper studies an efficient single-source alternative for transferable attacks on semantic segmentation. We formulate transferable attack composition as a chained computation over differentiable attack components, allowing the expensive source-model gradient computation to be shared. To reduce the update instability introduced by chained composition, we further use an integrated-gradient-style path-averaged direction as an empirical stabilization heuristic. Experiments on Pascal VOC and Cityscapes evaluate the resulting transferability efficiency trade-off across CNN- and transformer-based segmentation models. IGME achieves competitive transferability compared with single-source baselines and favorable runtime compared with model-ensemble attacks, while requiring access to only one source model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。