用结构化生成视角提升雷达图像抗干扰能力
Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification
- 通过几何条件生成多视角雷达图，替代传统噪声扰动
- 在FGSM、PGD等攻击下鲁棒性显著提升，准确率更高
- 适合雷达目标识别等结构化传感领域的安全应用
深度神经网络易受对抗扰动影响，限制其在合成孔径雷达（SAR）自动目标识别（ATR）等安全关键场景中的部署。随机平滑通过在噪声输入上平均预测结果来增强鲁棒性，但各向同性噪声常破坏SAR图像的语义结构。本文提出语义平滑，用由新视角合成模型生成的结构化随机变换取代基于噪声的扰动。针对SAR，模型基于成像几何条件合成多个合理的雷达视图，聚合生成视图上的预测以形成鲁棒分类器。实验表明，该方法在标准攻击（如FGSM、PGD）和SAR特定攻击（如OTSA、SMGAA）下均提升鲁棒性，同时提高干净样本分类准确率。结果表明，通过语义保持的几何变换进行随机平滑，是结构化感知领域对抗防御的有前景替代方案。
原文摘要 · Abstract (English)
Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recognition (ATR). Randomized smoothing improves robustness by averaging predictions over noisy inputs, but isotropic noise often fails to preserve the semantic structure of SAR imagery. We propose semantic smoothing, a defense that replaces noised-based perturbations with structured randomized transformations generated by a novel view synthesis model. For SAR, we condition on acquisition geometry to synthesize multiple plausible radar views. Predictions across generated randomized views are aggregated to form a robust classifier. Experiments show that semantic smoothing improves robustness against standard attacks, such as FGSM and PGD, and SAR-specific attacks, such as OTSA and SMGAA, while also increasing clean classification accuracy. These results demonstrate that randomized smoothing via semantically preserving geometric transformations is a promising alternative to isotropic noise for adversarial defense in structured sensing domains.
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。