Enhancing Adversarial Robustness with Signed Distance Fields for Harmonizing Geometric Invariance and Texture
Researchers have developed a new framework called GeoTexPuri to improve the adversarial robustness of deep neural networks in computer vision. This method harmonizes geometric structures with textural features by using Signed Distance Fields to guide the training process, creating stable anchors against pixel noise. Experiments on ImageNet show GeoTexPuri achieves high clean and robust accuracy while functioning as a deterministic classifier during inference without additional computational costs. AI
IMPACT This research could lead to more secure AI image recognition systems, reducing vulnerability to adversarial attacks in real-time applications.