Intrusion Detection Systems (IDS) represent a cornerstone of modern network security strategies, offering diverse methods and architectures to analyze network access. These structures can be as two categories: Signature and Anomaly. Signature - Based IDS monitor events using a database of known intrusions, while passive IDS focus on understanding system behavior and identifying anomalies. However, with the hasty development of the IoT, new and complex safety challenges possess emerged. Despite efforts to address IoT cybersecurity through various technologies, further development is essential to effectively safeguard IoT ecosystems. One promising approach to bolster IoT security involves leveraging machine learning techniques. Numerous studies have explored the application of DL also ML methods to progress Internet of Things safety. In our study, we have established a method that utilizes Deep Learning techniques to detect attacks on IoT systems. By employing Python programming and tools such as Tensorflow, Scikit-learn, and Seaborn, we have shown that deep learning models are effective detection accuracy. Our findings suggest that deep learning holds significant promise for bolstering IoT security measures, providing a more robust defense against cyber threats targeting IoT devices and networks. Through our research, we have contributed to progress the IoT security industry, addressing a critical need in the constantly changing field of cybersecurity.