In the last decade, the devices and appliances utilizing the Internet of things (IoT) have expanded tremendously, which has led to revolutionary developments in the network industry. Smart homes and cities, wearable devices, traffic monitoring, health systems, and energy savings are typical IoT applications. The diversity in IoT standards, protocols, and computational resources makes them vulnerable to security attackers. Botnets are challenging security threats in IoT devices that cause severe Distributed Denial of Service (DDoS) attacks. Intrusion detection systems (IDS) are necessary for safeguarding Internet-connected frameworks and enhancing insufficient traditional security countermeasures, including authentication and encryption techniques. This paper proposes a wrapper feature selection model (SSA–ALO) by hybridizing the salp swarm algorithm (SSA) and ant lion optimization (ALO). The new model can be integrated with IDS components to handle the high-dimensional space problem and detect IoT attacks with superior efficiency. The experiments were performed using the N-BaIoT benchmark dataset, which was downloaded from the UCI repository. This dataset consists of nine datasets that represent real IoT traffic. The experimental results reveal the outperformance of SSA–ALO compared to existing related approaches using the following evaluation measures: TPR (true positive rate), FPR (false positive rate), G-mean, processing time, and convergence curves. Therefore, the proposed SSA–ALO model can serve IoT applications by detecting intrusions with high true positive rates that reach 99.9% and with a minimal delay even in imbalanced intrusion families.

中文翻译：

---

使用 Salp Swarm 和 Ant Lion 混合优化模型的物联网僵尸网络检测

在过去的十年中，利用物联网 (IoT) 的设备和电器得到了极大的扩展，这导致了网络行业的革命性发展。智能家居和城市、可穿戴设备、交通监控、健康系统和节能是典型的物联网应用。物联网标准、协议和计算资源的多样性使它们容易受到安全攻击者的攻击。僵尸网络正在挑战物联网设备中的安全威胁，这些威胁会导致严重的分布式拒绝服务 (DDoS) 攻击。入侵检测系统 (IDS) 是保护 Internet 连接框架和增强不足的传统安全对策（包括身份验证和加密技术）所必需的。本文通过混合salp swarm算法（SSA）和蚁狮优化（ALO），提出了一种包装器特征选择模型（SSA-ALO）。新模型可以与IDS组件集成，以处理高维空间问题并以更高的效率检测物联网攻击。实验是使用从 UCI 存储库下载的 N-BaIoT 基准数据集进行的。该数据集由代表真实物联网流量的九个数据集组成。实验结果表明，与现有相关方法相比，SSA-ALO 的性能优于使用以下评估指标：TPR（真阳性率）、FPR（假阳性率）、G 均值、处理时间和收敛曲线。因此，所提出的 SSA-ALO 模型可以通过检测具有高达 99 的高真阳性率的入侵来为物联网应用服务。