Patch Synthesis for Property Repair of Deep Neural Networks

• DOI: 10.48550/arxiv.2404.01642
• Publication Date: 2024-01-01
• Authors: Chi, Zhiming; Ma, Jianan; Yang, Pengfei; Huang, Cheng-Chao; Li, Renjue; Huang, Xiaowei; Zhang, Lijun
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Cryptography and Security; Cryptography and Security (cs.CR); Machine Learning (cs.LG)

Deep neural networks (DNNs) are prone to various dependability issues, such as adversarial attacks, which hinder their adoption in safety-critical domains. Recently, NN repair techniques have been proposed to address these issues while preserving original performance by locating and modifying guilty neurons and their parameters. However, existing repair approaches are often limited to specific data sets and do not provide theoretical guarantees for the effectiveness of the repairs. To address these limitations, we introduce PatchPro, a novel patch-based approach for property-level repair of DNNs, focusing on local robustness. The key idea behind PatchPro is to construct patch modules that, when integrated with the original network, provide specialized repairs for all samples within the robustness neighborhood while maintaining the network's original performance. Our method incorporates formal verification and a heuristic mechanism for allocating patch modules, enabling it to defend against adversarial attacks and generalize to other inputs. PatchPro demonstrates superior efficiency, scalability, and repair success rates compared to existing DNN repair methods, i.e., realizing provable property-level repair for 100% cases across multiple high-dimensional datasets.