Network Intrusion detection systems are essential for the protection of advanced communication networks. Originally, these systems were hard-coded to identify specific signatures, patterns and rule violations; now artificial intelligence and machine learning algorithms provide promising alternatives. However, in the literature, various outdated datasets as well as a plethora of different evaluation metrics are used to prove algorithm efficacy. To enable a global comparison, this study compiles algorithms for different configurations to create common ground and proposes two new evaluation metrics. These metrics, the detection score and the identification score, together reliably present the performance of a network intrusion detection system to allow for practical comparison on a large scale. Additionally, we present a workflow to process raw packet flows into input features for machine learning. This framework quickly implements different algorithms for the various datasets and allows systematic performance comparison between those algorithms. Our experimental results, matching and surpassing the state-of-the-art, indicate the potential of this approach. As raw traffic input features are much easier and cheaper to extract when compared to traditional features, they show promise for application in real-time deep learning-based systems.
28 July 2025 in IEEE Transactions on Intelligent Transportation Systems
Over the past decade, it has been demonstrated that the In-Vehicle Network (IVN) of a modern Intelligent Transportation System (ITS) is vulnerable to several cyberattacks. Given the collaborative nature of these systems, detecting (remote) cyberattacks is of utmost importance in ensuring trusted interactions. One key technique that has been explored to detect adversarial presence in IVNs are Intrusion Detection Systems (IDSs). However, many existing solutions focus on legacy architectures or are not practically feasible due to their hardware requirements or inability to operate in real-time. To this end, we propose Modular Reduced Temporal Convolutional Network (MR-TCN), an efficient IDS architecture that can effectively be accelerated on hardware to enable real-time intrusion detection in low-cost embedded platforms. Additionally, we evaluate variants of MR-TCN on a Field-Programmable Gate Array (FPGA) platform across a diverse range of IVN traffic (i.e., CAN CC, CAN FD, and Automotive Ethernet), demonstrating its suitability in real-world applications.
Facial malformations such as overbite or underbite can be treated by maxillofacial surgery where the mandibula (i.e. the lower jaw) and/or maxilla (i.e. the upper jaw) is repositioned to obtain a preferential occlusion. These treatments need to be carefully planned prior to the actual operation. The planning of such surgery is an intensive and time consuming procedure in which the experience and knowledge of the surgeon plays a major role. As part of a CAD-based surgery planning, haptic interaction using 3D virtual models of the mandibula and maxilla, haptic feedback can make planning and surgery much more efficient. Haptic devices bridge the gap between the virtual environment and the physical world. An important step in such haptics based workflow is the collision detection between the two models at an update frequency of at least 1000 Hz. In this paper the possibility of the Implicit Sphere Tree algorithm as a collision detection algorithm tailored for this specific application is presented.