Narrow Results

Measurement-based profiling introduces intrusion in program execution. Intrusion effects can be mitigated by compensating for measurement overhead. Techniques for compensation analysis in performance profiling are presented and their implementation in the TAU performance system described. Experimental results on the NAS parallel benchmarks demonstrate that overhead compensation can be effective in improving the accuracy of performance profiling. However, parallel time profiling requires the execution delay introduced by measurement on individual processes to be communicated between processes when they interact. Parallel execution scenarios are given to model the effects and to determine the analysis procedures to be applied online.

The usage of the Internet of Things (IoT) in the field of transportation appears to have immense potential. Intelligent vehicle systems can exchange seamless information to assist cars to ensure better traffic control and road safety. The dynamic topology of this network, connecting a large number of vehicles, makes it vulnerable to several threats like authentication, data integrity, confidentiality, etc. These threats jeopardize the safety of vehicles, riders, and the entire system. Researchers are developing several approaches to combat security threats in connected and autonomous vehicles. Artificial Intelligence is being used by both scientists and hackers for protecting and attacking the networks, respectively. Nevertheless, wirelessly coupled cars on the network are in constant peril. This motivated us to develop an intrusion detection model that can be run in low-end devices with low processing and memory capacity and can prevent security threats and protect the connected vehicle network. This research paper presents an Attention-enabled Hierarchical Deep Neural Network (AHDNN) as a solution to detect intrusion and ensure autonomous vehicles’ security both at the nodes and at the network level. The proposed AHDNN framework has a very low false negative rate of 0.012 ensuring a very low rate of missing an intrusion in normal communication. This enables enhanced security in vehicular networks.

Detecting intrusions in real-time within cloud networks presents a multifaceted challenge involving intricate processes such as feature representation, intrusion type classification and post-processing procedures. Distributed Intrusion Detection Systems (DIDSs) constitute a complex landscape characterized by diverse contextual nuances, distinct functional advantages and limitations specific to deployment scenarios. Despite these challenges, DIDS offers immense potential for addressing evolving intrusion detection challenges through tailored contextual adaptations and unique functional advantages. Moreover, exploring the limitations associated with different deployment contexts facilitates targeted improvements and refinements, unlocking new avenues for innovation in intrusion detection technologies. Notably, deep learning (DL) integrated with blockchain technology emerges as a superior approach in terms of security, while bioinspired models excel in Quality of Service (QoS). These models demonstrate higher accuracy across various network scenarios, underscoring their efficacy in intrusion detection. Additionally, edge-based models exhibit high accuracy and scalability with reduced delay, complexity and cost in real-time network environments. The fusion of these models holds promise for enhancing classification performance across diverse attack types, offering avenues for future research exploration. This text conducts a comprehensive comparison of performance metrics, including accuracy, response delay, computational complexity, scalability and deployment costs. The proposed Novel DIDS Rank (NDR) streamlines model selection by considering these metrics, enabling users to make well-informed decisions based on multiple performance aspects simultaneously. This unified ranking approach facilitates the identification of DIDS that achieves high accuracy and scalability while minimizing response delay, cost and complexity across varied deployment scenarios.

The Information Technology products are suffering from various security issues due to the flaws residing in the software system. These flaws allow the violations of security policy and leads into vulnerability. Once the associated user discovers vulnerability the number of intrusions increases until the vendor releases a patch. The patching process helps in maintaining the stability of the software and reduces the probability of damage potential. Even after diffusion and installation whether the patch has successfully removed the vulnerability or not is of great importance. Patch failures creates more vulnerabilities and leads into disaster for developing organizations and users. Thus the success rate of patch is also an unavoidable factor on the basis of which the intrusion rate can be judged. Here in this paper we propose a vulnerability patch modeling that addresses the patching of vulnerabilities that are either discovered by external user or internal user. We also discuss after installation what leads a patch towards failure and what will be its impact on an intact system. The model also provides measures to estimate the potential unsuccessful patch rate that will help developers in logistic planning while patch development. We have used three datasets of different domain to validate the model. A numerical with different goodness of fit criteria is also illustrated in the paper.

Intrusion is one of the biggest problems in wireless sensor networks. Because of the evolution in wired and wireless mechanization, various archetypes are used for communication. But security is the major concern as networks are more prone to intrusions. An intrusion can be dealt in two ways: either by detecting an intrusion in a wireless sensor network or by preventing an intrusion in a wireless sensor network. Many researchers are working on detecting intrusions and less emphasis is given on intrusion prevention. One of the modern techniques for averting intrusions is through fuzzy logic. In this paper, we have defined a fuzzy rule-based system to avert intrusions in wireless sensor network. The proposed system works in three phases: feature extraction, membership value computation and fuzzified rule applicator. The proposed method revolves around predicting nodes in three categories as “red”, “orange” and “green”. “Red” represents that the node is malicious and prevents it from entering the network. “Orange” represents that the node “might be malicious” and marks it suspicious. “Green” represents that the node is not malicious and it is safe to enter the network. The parameters for the proposed FzMAI are packet send to base station, energy consumption, signal strength, a packet received and PDR. Evaluation results show an accuracy of 98.29% for the proposed system. A detailed comparative analysis concludes that the proposed system outperforms all the other considered fuzzy rule-based systems. The advantage of the proposed system is that it prevents a malicious node from entering the system, thus averting intrusion.