The last few years have seen the great potential of artificial intelligence (AI) technology to efficiently and effectively deal with an incredible deluge of data generated by the Internet of Things (IoT) devices. If all the massive data is transferred to the cloud for intelligent processing, it not only brings considerable challenges to the network bandwidth but also cannot meet the needs of AI applications that require fast and real-time response. Therefore, to achieve this requirement, mobile or multiaccess edge computing (MEC) is receiving a substantial amount of interest, and its importance is gradually becoming more prominent. However, with the emerging of edge intelligence, AI also suffers from several tremendous security threats in AI model training, AI model inference, and private data. This paper provides three novel defense strategies to tackle malicious attacks in three aspects. First of all, we introduce a cloud-edge collaborative antiattack scheme to realize a reliable incremental updating of AI by ensuring the data security generated in the training phase. Furthermore, we propose an edge-enhanced defense strategy based on adaptive traceability and punishment mechanism to effectively and radically solve the security problem in the inference stage of the AI model. Finally, we establish a system model based on chaotic encryption with the three-layer architecture of MEC to effectively guarantee the security and privacy of the data during the construction of AI models. The experimental results of these three countermeasures verify the correctness of the conclusion and the feasibility of the methods.

中文翻译：

---

边缘计算环境中部署的新型人工智能防御方案

在过去的几年中，人工智能（AI）技术具有巨大的潜力，可以有效地处理物联网（IoT）设备生成的大量数据。如果将所有海量数据都传输到云中进行智能处理，这不仅给网络带宽带来了巨大挑战，而且还不能满足需要快速实时响应的AI应用程序的需求。因此，为了达到这一要求，移动或多访问边缘计算（MEC）引起了人们的极大兴趣，并且其重要性逐渐变得更加突出。但是，随着边缘智能的兴起，AI在AI模型训练，AI模型推理和私有数据方面也遭受了数种巨大的安全威胁。本文从三个方面提供了三种新颖的防御策略来应对恶意攻击。首先，我们引入了一种云边缘协作式反攻击方案，以通过确保训练阶段生成的数据安全性来实现对AI的可靠增量更新。此外，我们提出了一种基于自适应溯源和惩罚机制的边缘增强防御策略，以有效，根本地解决AI模型推理阶段的安全问题。最后，我们建立了基于混沌加密的三层MEC体系结构模型，有效地保证了AI模型构建过程中数据的安全性和私密性。这三种对策的实验结果验证了结论的正确性和方法的可行性。