Cybersecurity in information technology (IT) infrastructures is one of the most significant and complex issues of the digital era. Increases in network size and associated data have directly affected technological breakthroughs in the Internet and communication areas. Malware attacks are becoming increasingly sophisticated and hazardous as technology advances, making it difficult to detect an incursion. Detecting and mitigating these threats is a significant issue for standard analytic methods. Furthermore, the attackers use complex processes to remain undetected for an extended period. The changing nature and many cyberattacks require a quick, adaptable, and scalable defense system. For the most part, traditional machine learning-based intrusion detection relies on only one algorithm to identify intrusions, which has a low detection rate and cannot handle large amounts of data. To enhance the performance of intrusion detection systems, a new deep multilayer classification approach is developed. This approach comprises five modules: preprocessing, autoencoding, database, classification, and feedback. The classification module uses an autoencoder to decrease the number of dimensions in a reconstruction feature. Our method was tested against a benchmark dataset, NSL-KDD. Compared to other state-of-the-art intrusion detection systems, our methodology has a 96.7% accuracy.
28 February 2018 in International Journal of Intelligent Engineering and Systems
The hybrid cloud is a secure alternative for enterprises to exploit the benefits of cloud computing to overcome the privacy and security concerns of data in IoT networks. However, in hybrid cloud IoT, sensitive items such as keys in the private cloud can become compromised due to internal attacks. Once these keys are compromised, the encrypted data in the public cloud are no longer secure. This work proposes a secure multilevel privacy-protection scheme based on Generative Adversarial Networks (GAN) for hybrid cloud IoT. The scheme secures sensitive information in the private cloud against internal compromises. GAN is used to generate a mask with the input of sensory data-transformation values and a trapdoor key. GAN’s effectiveness is thoroughly assessed using Peak Signal-to-Noise Ratio (PSNR), computation time, retrieval time, and storage overhead frameworks. The obtained results reveal that the security scheme being proposed is found to require a negligible storage overhead and a 4% overhead for upload/retrieval compared to the existing works.
The Internet of Things (IoT) is a broad term that refers to the collection of information about all of the items that are linked to the Internet. It supervises and controls the functions from a distance, without the need for human interaction. It has the ability to react to the environment either immediately or via its previous experiences. In a similar vein, robots may learn from their experiences in the environment that is relevant to their applications and respond appropriately without the need for human interaction. A greater number of sensors are being distributed across the environment in order to collect and evaluate the essential information. They are gaining ground in a variety of industries, ranging from the industrial environment to the smart home. Sensors are assisting in the monitoring and collection of data from all of the real-time devices that are reliant on all of the different types of fundamental necessities to the most advanced settings available. This research study was primarily concerned with increasing the efficiency of the sensing and network layers of the Internet of Things to increase cyber security. Due to the fact that sensors are resource-constrained devices, it is vital to provide a method for reacting, analysing, and transmitting data collected from the sensors to the base station as efficient as possible. Resource requirements, such as energy, computational power, and storage, vary depending on the kind of sensing devices and communication technologies that are utilised to link real-world objects together. Sensor networks' physical and media access control layers, as well as their applications in diverse geographical and temporal domains, are distinct from one another. Transmission coverage range, energy consumption, and communication technologies differ depending on the application requirements, ranging from low constraints to high resource enrich gadgets. This has a direct impact on the performance of the massive Internet of Things environment, as well as the overall network lifetime of the environment. Identifying and communicating matching items in a massively dispersed Internet of Things environment is critical in terms of spatial identification and communication.