A survey on Deep learning approaches for development more robust and reliable IDS models

  • Animesh Singh, Manish Ahirwar, Piyush Kumar Shukla
Keywords: AI, Auto-Encoders, Convolution Neural Networks, Deep learning, Machine learning, PCA.


Introduction-Internet-based assaults have facilitated the development of defensive mechanisms. To safeguard the local Network, systems such as a firewall and anti-virus software have been created. However, because the firewall and anti-virus designs are not updated, new threats can be devised. Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS) have been created to address this issue. Intrusion detection systems (IDS) are systems that are meant to identify assaults that originate from the Internet or a local network and cause harm to network systems. They may be composed of a variety of packets and data to maintain data security. Their primary objective is to identify assaults and, if necessary, to prevent them. Intrusion Detection Systems can gather extensive information about the most frequent types of attacks and their perpetrators. With the advent of the endless communication model and more and more digital devices on the Network, cybersecurity concerns to protect the system's information or communication technology are increasing. Intruders create new attack patterns every day. Therefore, to prevent these attacks, an intrusion detection system (IDS) must first identify them correctly and then respond appropriately. Extensive research in machine learning has lately resulted in a significant advance in the field of brain imitation. The breakthrough in machine learning comes from deep learning, which is predicted to revolutionize the area of artificial intelligence. When cyber security and deep learning are combined, we can get remarkable results. Previously, researchers used a variety of machine learning techniques to detect and prevent attacks

How to Cite
Piyush Kumar Shukla, A. S. M. A. (2021). A survey on Deep learning approaches for development more robust and reliable IDS models. Design Engineering, 2700-2715. Retrieved from http://thedesignengineering.com/index.php/DE/article/view/5191