The development of 5G has substantially increased the destructiveness of DoS/DDoS attacks because the data processing capability of computers has not been accordingly enhanced, and this contradiction creates a vulnerability for attackers to compromise a server by sending a massive data flow. in practical 5G circumstances, it is difficult to extract distinct features between malicious and benign massive data flows. This amplifies the difficulties of DoS/DDoS detection. Thus, precautions against DoS/DDoS attack in 5G are of great importance. in this article, we present a solution based on smart contracts and machine learning as a countermeasure against DoS/DDoS attacks in the 5G background by hiding a protected server in a blockchain network and flexibly restricting the scale of DoS/DDoS via transaction fees. We also leverage non-repudiation of smart contracts, analyzing users' malicious behavior of communication and executing punishment via smart contracts. Our scheme could effectively mitigate massive DoS/DDoS attacks in advance and dynamically punitively charge DoS/DDoS attacks. Compared to existing DoS/DDoS defense in 4G, our scheme offers numerous benefits, including making benign communication always dominate rational users and countering DoS/DDoS attacks before they are launched. Moreover, compared to common DoS/DDoS detection based on Ai, we consider the source trustworthiness of training samples and take measures to avoid backdoors where model trainers may compromise Ai models to launch DoS/DDoS attacks.

中文翻译：

---

5G环境下基于智能合约和人工智能的DoS/DDoS攻击对策


5G的发展使得DoS/DDoS攻击的破坏性大幅增加，因为计算机的数据处理能力并没有相应增强，这种矛盾为攻击者通过发送海量数据流破坏服务器创造了漏洞。在实际的5G环境中，很难提取恶意和良性海量数据流之间的明显特征。这加大了 DoS/DDoS 检测的难度。因此，防范5G中的DoS/DDoS攻击非常重要。在本文中，我们提出了一种基于智能合约和机器学习的解决方案，通过将受保护的服务器隐藏在区块链网络中，并通过交易费用灵活限制DoS/DDoS规模，作为5G背景下DoS/DDoS攻击的对策。我们还利用智能合约的不可否认性，分析用户的恶意通信行为并通过智能合约执行惩罚。我们的方案可以有效提前缓解大规模DoS/DDoS攻击，并对DoS/DDoS攻击进行动态惩罚性计费。与 4G 中现有的 DoS/DDoS 防御相比，我们的方案提供了许多好处，包括使良性通信始终主导理性用户以及在 DoS/DDoS 攻击发起之前对其进行反击。此外，与基于Ai的常见DoS/DDoS检测相比，我们考虑了训练样本的来源可信度，并采取措施避免模型训练者可能损害Ai模型发起DoS/DDoS攻击的后门。