AdvGLOW: Covert adversarial attacks against autonomous driving perception

This paper proposes AdvGLOW, a framework generating covert adversarial attacks against autonomous driving perception systems. It uses a Glow-based reversible neural network for bi-directional image-latent space transformation, crafting imperceptible perturbations. Coupling layers and actnorm ensure invertible, effective transformations. The method achieves real-time generation (<50 ms). Experiments on driving datasets and models confirm its stealth and effectiveness, pioneering the use of normalizing flows for physically realizable attacks in this context. Repository includes code and configurations.