Aug 2026
Enhancing adversarial robustness of lightweight neural networks for on-vehicle traffic sign recognition systems
TRADES-JR, a TRADES loss function guided by Jacobian regularization, is proposed, which enables LNNs to maintain robust and high-accuracy traffic sign recognition even in adversarial environments, thereby enhancing the reliability of the autonomous driving system.
YunKai Zhao, Shang Gao, Jieliang Zhao
· Proceedings of the Instituti... · 0 citations