Over the past few years, deep neural networks (DNNs) have achieved tremendous success and have been continuously applied in many application domains. However, during the practical deployment in the industrial tasks, DNNs are found to be erroneous-prone due to various reasons such as overfitting, lacking robustness to real-world corruptions during practical usage. To address these challenges, many recent attempts have been made to repair DNNs for version updates under practical operational contexts by updating weights (i.e., network parameters) through retraining, fine-tuning, or direct weight fixing at a neural level. In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i.e., block) level. We first perform empirical studies to investigate the limitation of whole network-level and layer-level repairing, which motivates us to explore a novel repairing direction for DNN repair at the block level. To this end, we first propose adversarial-aware spectrum analysis for vulnerable block localization that considers the neurons' status and weights' gradients in blocks during the forward and backward processes, which enables more accurate candidate block localization for repairing even under a few examples. Then, we further propose the architecture-oriented search-based repairing that relaxes the targeted block to a continuous repairing search space at higher deep feature levels. By jointly optimizing the architecture and weights in that space, we can identify a much better block architecture. We implement our proposed repairing techniques as a tool, named ArchRepair, and conduct extensive experiments to validate the proposed method. The results show that our method can not only repair but also enhance accuracy & robustness, outperforming the state-of-the-art DNN repair techniques.

翻译：过去几年来,深神经网络(DNN)取得了巨大成功,并被持续应用于许多应用领域。然而,在工业任务的实际部署期间,DNN由于各种原因,例如超装、在实际使用期间对真实世界腐败缺乏强力等原因,发现DNN具有错误易发性。为了应对这些挑战,最近多次尝试通过更新重量(即网络参数),在实际操作背景下更新DNN更新版本更新。为此,我们首先建议通过在神经层面更新重量(即网络参数),对脆弱的区块进行对称波谱分析,该分析将考虑到神经元的状态和重量在深度调整。在这项工作中,我们首先尝试通过在更高(即块块)水平上联合优化结构和重量来修复DNNNN。我们首先进行实证性研究,以调查整个网络层面和层层面修复的局限性。这促使我们探索新式的DNNN的修复方向。为此,我们首先提议对基于网络的系统进行对抗性观测频谱分析,但考虑到神经元的状态和重量在深度上的深度,而不是在深重度上,我们在前方和后方块的修理过程中开始修复技术,然后进行更精确的修复。让我们的建筑进行更精确的搜索,从而显示一个更精确的建筑结构,从而显示更精确的校正的建筑结构。