让神经网络更易验证，通过保持神经元行为一致
Training Verification-Friendly Neural Networks via Neuron Behavior Consistency
- 训练时强制邻近输入下神经元激活状态一致
- 在多个数据集上验证时间显著缩短，且随扰动半径增大仍有效
- 适合需要高可信度的AI安全场景，如自动驾驶
形式化验证为神经网络提供关键安全保障，但实际应用受限于验证耗时。本文提出一种训练验证友好型神经网络的新方法，该网络兼具鲁棒性、易验证性和较高精度。通过在训练中引入神经元行为一致性，使神经元激活状态在局部邻域内保持稳定，减少不稳定神经元数量并收紧神经元边界，从而提升网络可验证性。我们在MNIST、Fashion-MNIST和CIFAR-10数据集上，使用多种网络结构进行了评估。实验结果表明，采用本方法训练的网络在不同扰动半径和架构下均表现出良好可验证性，而其他方法在半径增大时验证能力迅速下降。此外，本方法可与现有技术结合，进一步提升网络可验证性。
原文摘要 · Abstract (English)
Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks, which are robust, easy to verify, and relatively accurate. Our method integrates neuron behavior consistency into the training process, making neuron activation states remain consistent across different inputs within a local neighborhood. This reduces the number of unstable neurons and tightens the bounds of neurons thereby enhancing the network's verifiability. We evaluated our method using the MNIST, Fashion-MNIST, and CIFAR-10 datasets with various network architectures. The experimental results demonstrate that networks trained using our method are verification-friendly across different radii and architectures, whereas other tools fail to maintain verifiability as the radius increases. Additionally, we show that our method can be combined with existing approaches to further improve the verifiability of networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。