As the Internet of Things (IoT) continues to expand, the number of connected devices is expected to increase significantly. While IoT devices offer various benefits across different applications, they also become attractive targets for cyber-attackers looking to compromise the IoT network. One hazardous type of network attack is the Man-In-The-Middle (MITM) attack, where attackers eavesdrop on the data exchange between two users. This type of attack can have a severe impact, potentially leading to further attacks, such as phishing. To address this issue, the study explores the use of Deep Learning techniques for detecting MITM attacks. Deep Learning supports various techniques which can detect the MITM attacks on the IoT network. In this paper, the authors have compared two deep learning techniques, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to detect MITM attacks on the IoT network after training the models on the MITM attack dataset. Additionally, the study incorporates a feature selection method called Random Forest Classifier and two feature scaling methods, Standard and Min-Max Scaler, applied to the data before constructing the model. The research utilizes three datasets from the Kitsune Network Attack Dataset to analyze and validate the effectiveness of these detection techniques. The initial two sections of the paper present the topic and its relevant background. Following that, the third section outlines the steps taken in the current study, while the fourth section delves into the study’s findings. The final section serves as a conclusion, offering insights and outlining potential future directions for research. From the analysis of the results, it is concluded that the CNN technique performs the best in detecting MITM attacks by achieving more performance evaluation metrics using all the three different datasets.