Adversarial vulnerability and lack of interpretability are critical limitations of deep neural networks, especially in safety-sensitive settings such as autonomous driving. We introduce \DesignII, a neuro-symbolic framework that integrates symbolic rule supervision into neural networks to enhance both adversarial robustness and explainability. Domain knowledge is encoded as logical constraints over appearance attributes such as shape and color, and enforced through semantic and symbolic logic losses applied during training. Using the GTSRB dataset, we evaluate robustness against FGSM and PGD attacks at a standard $\ell_\infty$ perturbation budget of $\varepsilon = 8/255$. Relative to clean training, standard adversarial training provides modest improvements in robustness ($\sim$10 percentage points). Conversely, our FGSM-Neuro-Symbolic and PGD-Neuro-Symbolic models achieve substantially larger gains, improving adversarial accuracy by 18.1\% and 17.35\% over their corresponding adversarial-training baselines, representing roughly a three-fold larger robustness gain than standard adversarial training provides when both are measured relative to the same clean-training baseline, without reducing clean-sample accuracy. Compared to transformer-based defenses such as LNL-MoEx, which require heavy architectures and extensive data augmentation, our PGD-Neuro-Symbolic variant attains comparable or superior robustness using a ResNet18 backbone trained for 10 epochs. These results show that symbolic reasoning offers an effective path to robust and interpretable AI.

翻译：对抗性脆弱性和缺乏可解释性是深度神经网络的关键局限，尤其在自动驾驶等安全敏感场景中。我们提出NeuroShield，一种将符号规则监督集成到神经网络中以增强对抗鲁棒性和可解释性的神经符号框架。领域知识被编码为关于形状、颜色等外观属性的逻辑约束，并通过训练过程中应用的语义与符号逻辑损失进行强制约束。基于GTSRB数据集，我们在标准$\ell_\infty$扰动预算$\varepsilon = 8/255$下评估针对FGSM和PGD攻击的鲁棒性。相较于干净训练，标准对抗训练仅带来有限的鲁棒性提升（约10个百分点）。相比之下，我们的FGSM-Neuro-Symbolic与PGD-Neuro-Symbolic模型取得了显著更大的增益，对抗精度分别比对应对抗训练基线提升18.1%和17.35%，相当于以相同干净训练基线衡量时，其鲁棒性增益约为标准对抗训练的三倍，且未降低干净样本精度。与LNL-MoEx等需要复杂架构和大量数据增强的基于Transformer的防御方法相比，我们的PGD-Neuro-Symbolic变体仅使用训练10个周期的ResNet18骨干网络即可达到相当或更优的鲁棒性。这些结果表明符号推理为构建鲁棒且可解释的AI提供了有效路径。