Aug 2026· Proceedings of the Institution of mechanical engineers. Part D, journal of automobile engineering· 0 citations· 16 references
TL;DR
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.
Abstract
In recent years, with the rapid development of autonomous driving technology, lightweight neural networks (LNNs) have been increasingly applied in-vehicle and edge computing devices. A growing number of studies have focused on deploying LNNs in resource-constrained environments to achieve real-time traffic sign recognition, obstacle detection, and other tasks. However, while LNNs maintain high inference efficiency, their robustness has become an increasingly important concern. Research has shown that adversarial attacks targeting traffic signs can significantly disrupt the predictions of LNNs, leading to misclassifications. To enhance the adversarial robustness of LNNs, we propose TRADES-JR, a TRADES loss function guided by Jacobian regularization. This approach simultaneously considers the prediction distribution differences between clean and adversarial samples while penalizing the Frobenius norm of the network output’s Jacobian with respect to the input. By constraining the sensitivity to input perturbations, our method enhances the adversarial robustness of LNNs. We evaluate the proposed algorithm on the GTSRB and TSRD datasets. The results demonstrate that our method significantly improves the adversarial robustness of LNNs under both white-box and black-box attacks. Therefore, this method enables LNNs to maintain robust and high-accuracy traffic sign recognition even in adversarial environments, thereby enhancing the reliability of the autonomous driving system.
Among the evaluated models, CNNs exhibit the highest baseline robustness, whereas DNNs and RNNs rely more heavily on defense mechanisms to maintain performance, whereas DNNs and RNNs rely more heavily on defense mechanisms to maintain performance.
Surekha M., A. K. Sagar, Vineeta Khemchandani· International Journal of Int...· 0 citations
With the development of artificial intelligence and intelligent algorithms, new technical methods of automatic military target recognition in complex environments have been provided. However, limited availability of labeled samples, significant scale variations in targets and computing resource limitations on embedded devices all still limit detection accuracy and the ability to deploy detection in real-time. In this regard, a generative adversarial network (GAN) based few-shot military target detection is presented. To enlarge the training data set, class-conditional sample generation, multi-scale feature encoding, target-region attention constraints and generated-sample quality screening are employed, and the joint training of real and generated samples is used to enhance the generalization ability of the model. Based on this, depthwise separable convolution, channel pruning, structural re-parameterization, mixed-precision quantization, knowledge distillation, and operator fusion are introduced to realize lightweight network design and optimize the network on the edge. Experimental results show that the proposed method achieves a precision of 91.2%, a recall of 88.9%, and an F1-score of 90.0%. The mAP@0.5 and mAP@0.5:0.95 reach 92.7% and 61.8%, respectively, while the model contains only 4.1 M parameters and requires 7.6 G FLOPs. On the NVIDIA Jetson Orin NX platform, the inference speed reaches 106.4 FPS. These results demonstrate that the method effectively balances few-shot detection accuracy, robustness in complex environments, and real-time inference requirements on embedded edge devices.
This research investigates the adversarial robustness of lane detection for Autonomous Vehicles (AVs) under challenging driving conditions using Generative Adversarial Networks (GANs). In this work, the term adversarial refers to the adversarial training mechanism of GANs and to robustness under naturally adverse driving conditions, particularly illumination variation, rather than to defence against deliberate pixel-level perturbation attacks such as FGSM or PGD. Lane detection is a crucial component for safe navigation, but it often fails under poor lighting or adverse weather. To solve this, a U-Net model is trained on the Berkeley DeepDrive (BDD100K) dataset as a baseline. Then, Conditional GAN (CGAN) is used with the Cityscapes dataset to learn the mapping between RGB images and lane masks, which improves structural consistency. To handle illumination changes, CycleGAN is used to simulate Day-to-Night and Night-to-Day translations using BDD100K datasets, creating a more diverse training set. Preprocessing involves resizing images to 512×512 to ensure training efficiency on limited GPU hardware. The experiments are conducted using TensorFlow in a GPU-accelerated environment. Results show that the U-Net + CycleGAN model achieves a Precision of 65.41% and an F1-Score of 63.79%, which outperforms previous studies. The CGAN model also shows high performance with 92.55% F1-Score. This research proves that using GANs for data augmentation and domain translation can enhance the adversarial robustness and reliability of lane detection systems in real-world scenarios.
Brian Lee Chong Ming, Thinesh Ganesan· International Conference on...· 0 citations
A method to analyze ANNs designed for image classification from an adversarial robustness perspective and implemented an ablation and fine-tuning strategy that successfully boosted the robustness of the ANNs against a variant of the Auto-PGD attack under different threat models.
AdROD outperforms five baseline defenses and exhibits superior generalizability compared with the evaluated adversarial-training baselines, while maintaining real-time performance for safely stopping the vehicle at a stop sign instrumented with adversarial patches.
Yuting Wu, Dongfang Guo, Xiangzhong Luo et al.· 0 citations
The research methodology involved a systematic literature review using the Scopus database, adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, and focusing on recent advancements in attack and defence techniques.
