论文标题
可证明神经元激活模式的运行时间监测
Provably-Robust Runtime Monitoring of Neuron Activation Patterns
论文作者
论文摘要
为了使深度神经网络（DNN）用于安全至关重要的自主驾驶任务，如果DNN的输入类似于DNN培训中使用的数据，则希望监视操作时间。尽管监测DNN激活模式的最新结果为通过训练数据集构建抽象而提供了合理的保证，但由于轻微的输入扰动而降低假阳性，这是成功调整技术的问题。我们通过将正式的符号推理整合在监视器施工过程中，以应对这一挑战。该算法在应用抽象函数构建监视器之前，对具有扰动的输入（或特征）进行神经元值的声音最差估计。可证明的鲁棒性进一步推广到监测单个神经元可以使用多个位的情况下，这意味着人们可以对神经元值间隔进行精细颗粒的决定记录激活模式。
For deep neural networks (DNNs) to be used in safety-critical autonomous driving tasks, it is desirable to monitor in operation time if the input for the DNN is similar to the data used in DNN training. While recent results in monitoring DNN activation patterns provide a sound guarantee due to building an abstraction out of the training data set, reducing false positives due to slight input perturbation has been an issue towards successfully adapting the techniques. We address this challenge by integrating formal symbolic reasoning inside the monitor construction process. The algorithm performs a sound worst-case estimate of neuron values with inputs (or features) subject to perturbation, before the abstraction function is applied to build the monitor. The provable robustness is further generalized to cases where monitoring a single neuron can use more than one bit, implying that one can record activation patterns with a fine-grained decision on the neuron value interval.
