Robust Network Alignment via Attack Signal Scaling and Adversarial Perturbation Elimination

Abstract

Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial camouflage optimization through gradient back-propagation. However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance. Moreover, these approaches neglect diverse weather conditions, reducing the efficacy of generated camouflage across varying weather scenarios. To tackle these challenges, we propose a robust and accurate camouflage generation method, namely RAUCA. The core of RAUCA is a novel neural rendering component, Neural Renderer Plus (NRP), which can accurately project vehicle textures and render images with environmental characteristics such as lighting and weather. In addition, we integrate a multi-weather dataset for camouflage generation, leveraging the NRP to enhance the attack robustness. Experimental results on six popular object detectors show that RAUCA consistently outperforms existing methods in both simulation and real-world settings.

Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing

“…Fair Classification. Trustworthy machine learning has attracted active research in recent years (Palanisamy et al, 2018;Lei et al, 2019;Zhou et al, 2020;Zhang et al, 2020b;Zhou & Liu, 2019;Wu et al, 2021;Zhou et al, 2021b;Zhao et al, 2021;Ren et al, 2021; Ma et al, 2021;Zhang et al, 2021). Fair classification techniques aim to guarantee the learnt classifiers that are not only accurate but also fair with respect to sensitive attributes (Caton & Haas, 2020;Mehrabi et al, 2021).…”