A Vehicle Can Bus Anomaly Detection Method for Periodic Attacks Based on the Entropy Model

Because of the rapid development of automobile intelligence and networking, cyber attackers can invade the vehicle network via wired and wireless interfaces, such as physical interfaces, short-range wireless interfaces, and long-range wireless interfaces. Thus, interfering with regular driving will immediately jeopardises the drivers’ and passengers’ personal and property safety. To accomplish security protection for the vehicle CAN (Controller Area Network) bus, we propose an anomaly detection method by calculating the information entropy based on the number of interval messages during the sliding window. It detects periodic attacks on the vehicle CAN bus, such as replay attacks and flooding attacks. First, we calculate the number of interval messages according to the CAN bus baud rate, the number of bits of a single frame message, and the time required to calculate information entropy within the window. Second, we compute the window information entropy of regular packet interval packets and determine the normal threshold range by setting a threshold coefficient. Finally, we calculate the information entropy of the data to be measured, determine whether it is greater than or less than the threshold, and detect the anomaly. The experiment uses CANoe software to simulate the vehicle network. It uses the body frame CAN bus network of a brand automobile body bench as the regular network, simulates attack nodes to attack the regular network periodically, collects message data, and verifies the proposed detection method. The results show that the proposed detection method has lower false-negative and false-positive rates for attack scenarios such as replay attacks and flood attacks across different attack cycles.

Framework design for competitive marketing mechanism in Iraqi social media

Several organizations in Iraq manufacture similar commodities in this aggressive social trading. The objective of these organizations is diffusing information about their commodities publicly for popularity of the commodities in social media. More returns result in popular commodities and vice versa. The development of a framework incorporating two organizations engaging to broaden the information to the large media has been undertaken. The organizations first identified their initial seed points concurrently and then data was scattered as per the Independent Cascade Model (ICM). The major objective of the organizations is the identification of seed points for the diffusion of data to several points in social media. Significant is also how fast data diffusion can be done. Data effect will arise from either none, one or more nodes in a social interconnection. Evaluation is also accomplished on the number of fraction parts in various sections are affected by the different rates of data diffusion. The simulation result for suggested framework presented better outcomes result for random network 1 and random network 2 comparing with regular network. This framework is used a Hotellingframwork of competition.

Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations

Today’s deep learning systems deliver high performance based on end-to-end training but are notoriously hard to inspect. We argue that there are at least two reasons making inspectability challenging: (i) representations are distributed across hundreds of channels and (ii) a unifying metric quantifying inspectability is lacking. In this paper, we address both issues by proposing Semantic Bottlenecks (SB), which can be integrated into pretrained networks, to align channel outputs with individual visual concepts and introduce the model agnostic Area Under inspectability Curve (AUiC) metric to measure the alignment. We present a case study on semantic segmentation to demonstrate that SBs improve the AUiC up to six-fold over regular network outputs. We explore two types of SB-layers in this work. First, concept-supervised SB-layers (SSB), which offer inspectability w.r.t. predefined concepts that the model is demanded to rely on. And second, unsupervised SBs (USB), which offer equally strong AUiC improvements by restricting distributedness of representations across channels. Importantly, for both SB types, we can recover state of the art segmentation performance across two different models despite a drastic dimensionality reduction from 1000s of non aligned channels to 10s of semantics-aligned channels that all downstream results are based on.

Network intrusion detection using machine learning

In this research we have studied the use of machine learning techniques in detecting network intrusions. Most research in the field has used the very outdated dataset (KDDCup99) which consists of a set handcrafted features. In our research we present models that work well on both the older dataset and on newer datasets such as ISCX2014 and ISCX2012. We also present methods for extracting features from these datasets. Another issue we found with most research in this field is that they do not study the effect of surges in regular network traffic and how that might affect the model. We put our model to test in 10x traffic and show its effectiveness under these conditions. We also study how semi-supervised models can be used in training NIDS models without directly showing them labeled data.

Network intrusion detection using machine learning

In this research we have studied the use of machine learning techniques in detecting network intrusions. Most research in the field has used the very outdated dataset (KDDCup99) which consists of a set handcrafted features. In our research we present models that work well on both the older dataset and on newer datasets such as ISCX2014 and ISCX2012. We also present methods for extracting features from these datasets. Another issue we found with most research in this field is that they do not study the effect of surges in regular network traffic and how that might affect the model. We put our model to test in 10x traffic and show its effectiveness under these conditions. We also study how semi-supervised models can be used in training NIDS models without directly showing them labeled data.

How Does the Heterogeneity of Members Affect the Evolution of Group Opinions?

Understanding the impact of heterogeneity on the evolution of group opinions can enlighten us on how to effectively organize, redesign, and improve decision-making efficiency. This article explores mainly the effects of heterogeneity on the evolution of group opinions. It is found that the heterogeneity of individuals’ openness has an important influence on the ability to aggregate group opinions. According to the average amount of clusters and Herfindahl–Hirschman Index (HHI) under different network structures, heterogeneity often improves the ability. In addition, for the small-world network and random network, there is little difference in the aggregation ability from both the average amount of clusters and the Herfindahl–Hirschman Index. While for the regular network, the ability is obviously weaker than that of the other two. This result also shows that the randomness of interaction between members will enhance the cohesion of a group.

Adjusting the Regular Network of Squares Resolution to the Digital Terrain Model Surface Shape

A regular network of squares is formed by points uniformly distributed (mostly in the square corners) over the surface that is represented by the network. Each point (node) of the network has specified coordinates (X and Y) with a fixed constant distance between them. The third coordinate in a node (H) is determined by the application of interpolation based on the points distributed (usually dispersed as a point cloud e.g., from LiDAR) over the surface of the area surrounding the node. The regular network of squares formed in this manner allows the representation of a digital terrain model (DTM) to be performed in spatial information systems (SIP, GIS). The main problem that arises during the construction of such a network is the proper determination of its resolution (the base distance between the coordinates X and Y) depending on the topography. This article presents a method of the regular network of squares resolution determination depending on the morphological shape of the terrain surface. Following the application of the procedures being described, a differently shaped terrain is assigned various network densities. This enables the minimisation of inaccuracies of the surface model being formed. Consequently, a regular network of squares is formed with different base square sizes, which is adjusted with its resolution to the morphology of the surface it describes. Such operations allow the terrain model accuracy to be maintained over the entire area while reducing the number of points stored in the DTM database to the minimum.

Measuring event concentration in empirical networks with different types of degree distributions

Measuring event concentration often involves identifying clusters of events at various scales of resolution and across different regions. In the context of a city, for example, clusters may be characterized by the proximity of events in the metric space. However, events may also occur over urban structures such as public transportation and infrastructure systems, which are naturally represented as networks. Our work provides a theoretical framework to determine whether events distributed over a set of interconnected nodes are concentrated on a particular subset. Our main analysis shows how the proposed or any other measure of event concentration on a network must explicitly take into account its degree distribution. We apply the framework to measure event concentration (i) on a street network (i.e., approximated as a regular network where events represent criminal activities); and (ii) on a social network (i.e., a power law network where events represent users who are dissatisfied after purchasing the same product).

PROBLEM DOSTĘPNOŚCI TERENÓW ZIELENI W MIEŚCIE NA PRZYKŁADZIE ŁODZI

The article is devoted to the subject of urban greenery. The paper attempts to present real green areas and not only those that have such a purpose featuring in lists and registers. The authors also refer to the topic of availability of urban greenery for the residents of the city, taking into account an uneven density of places of residence. The aim of the article is to present the method for assessing the availability of green areas around places of residence, using spatial data showing residential buildings and official data on greenery. The relevant analyses are based on a regular network of squares of 90 m × 90 m. It was found that Łódź is a city with rich greenery resources. However, this judgment needs revising because a significant part of the residents both in their places of residence (R = 50 m) and further surroundings (R = 500 m) do not have access to green areas intended for recreation.

Toward a more Efficient Knowledge Network in Innovation Ecosystems: A Simulated Study on Knowledge Management

Knowledge management has become increasingly important in the era of knowledge economy. This study explores what is an optimal knowledge network for more efficient knowledge diffusion among strategic partners in order to provide insights on sustainable enterprises and a more knowledge-efficient innovation ecosystem. Based on simulated analyses of the efficiency of knowledge network models, including regular network, random network, and small world network, this study shows that a random knowledge network is more efficient for knowledge diffusion when a mixture knowledge trade rule is used. This study thus helps identify which knowledge networks facilitate knowledge exchange among collaborative partners for sustainable knowledge management. Management practitioners and policymakers can use the findings to design more appropriate knowledge exchange networks to improve the efficiency of knowledge diffusion in an innovation ecosystem.