Connected cars are vulnerable to cyber attacks. Security challenges arise from vehicular management uplinks, from signaling with roadside units or nearby cars, as well as from common Internet services. Major threats arrive from bogus traffic that enters the in-car backbone, which will comprise of Ethernet technologies in the near future. Various security techniques from different areas and layers are under discussion to protect future vehicles. In this paper, we show how Per-Stream Filtering and Policing of IEEE Time-Sensitive Networking (TSN) can be used as a core technology for identifying misbehaving traffic flows in cars, and thereby serve as network anomaly detectors. TSN is the leading candidate for implementing quality of service in vehicular Ethernet backbones. We classify the impact of network attacks on traffic flows and benchmark the detection performance in each individual class. Based on a backbone topology derived from a real car and its traffic definition, we evaluate the detection system in realistic scenarios with real attack traces. Our results show that the detection accuracy depends on the precision of the in-vehicle communication specification, the traffic type, the corruption layer, and the attack impact on the link layer. Most notably, the anomaly indicators of our approach remain free of false positive alarms, which is an important foundation for implementing automated countermeasures in future vehicles.
相關內容
Anomaly detection is one of the most active research areas in various critical domains, such as healthcare, fintech, and public security. However, little attention has been paid to scholarly data, i.e., anomaly detection in a citation network. Citation is considered as one of the most crucial metrics to evaluate the impact of scientific research, which may be gamed in multiple ways. Therefore, anomaly detection in citation networks is of significant importance to identify manipulation and inflation of citations. To address this open issue, we propose a novel deep graph learning model, namely GLAD (Graph Learning for Anomaly Detection), to identify anomalies in citation networks. GLAD incorporates text semantic mining to network representation learning by adding both node attributes and link attributes via graph neural networks. It exploits not only the relevance of citation contents but also hidden relationships between papers. Within the GLAD framework, we propose an algorithm called CPU (Citation PUrpose) to discover the purpose of citation based on citation texts. The performance of GLAD is validated through a simulated anomalous citation dataset. Experimental results demonstrate the effectiveness of GLAD on the anomalous citation detection task.
In this paper, we consider the problem of activity detection in grant-free code-domain non-orthogonal multiple access (NOMA). We focus on performing activity detection via subspace methods under a setup where the data and pilot spreading signatures are of different lengths, and consider a realistic frame-structure similar to existing mobile networks. We investigate the impact of channel correlation on the activity detection performance; first, we consider the case where the channel exhibits high correlation in time and frequency and show how it can heavily deteriorate the performance. To tackle that, we propose to apply user-specific masking sequences overlaid on top of the pilot signatures. Second, we consider the other extreme with the channel being highly selective, and show that it can also negatively impact the performance. We investigate possible pilots' reallocation strategies that can help reduce its impact.
Internet of Medical Things (IoMT) represents an application of the Internet of Things, where health professionals perform remote analysis of physiological data collected using sensors that are associated with patients, allowing real-time and permanent monitoring of the patient's health condition and the detection of possible diseases at an early stage. However, the use of wireless communication for data transfer exposes this data to cyberattacks, and the sensitive and private nature of this data may represent a prime interest for attackers. The use of traditional security methods on equipment that is limited in terms of storage and computing capacity is ineffective. In this context, we have performed a comprehensive survey to investigate the use of the intrusion detection system based on machine learning (ML) for IoMT security. We presented the generic three-layer architecture of IoMT, the security requirement of IoMT security. We review the various threats that can affect IoMT security and identify the advantage, disadvantages, methods, and datasets used in each solution based on ML. Then we provide some challenges and limitations of applying ML on each layer of IoMT, which can serve as direction for future study.
The increasing interaction of industrial control systems (ICSs) with public networks and digital devices introduces new cyber threats to power systems and other critical infrastructure. Recent cyber-physical attacks such as Stuxnet and Irongate revealed unexpected ICS vulnerabilities and a need for improved security measures. Intrusion detection systems constitute a key security technology, which typically monitor network data for detecting malicious activities. However, a central characteristic of modern ICSs is the increasing interdependency of physical and cyber network processes. Thus, the integration of network and physical process data is seen as a promising approach to improve predictability in intrusion detection for ICSs by accounting for physical constraints and underlying process patterns. This work systematically assesses real-time cyber-physical intrusion detection and multiclass classification, based on a comparison to its purely network data-based counterpart and evaluation of misclassifications and detection delay. Multiple supervised machine learning models are applied on a recent cyber-physical dataset, describing various cyber attacks and physical faults on a generic ICS. A key finding is that integration of physical process data improves detection and classification of all attack types. In addition, it enables simultaneous processing of attacks and faults, paving the way for holistic cross-domain cause analysis.
It has been a long time that computer architecture and systems are optimized to enable efficient execution of machine learning (ML) algorithms or models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: the improvement of designers' productivity, and the completion of the virtuous cycle. In this paper, we present a comprehensive review of work that applies ML for system design, which can be grouped into two major categories, ML-based modelling that involves predictions of performance metrics or some other criteria of interest, and ML-based design methodology that directly leverages ML as the design tool. For ML-based modelling, we discuss existing studies based on their target level of system, ranging from the circuit level to the architecture/system level. For ML-based design methodology, we follow a bottom-up path to review current work, with a scope of (micro-)architecture design (memory, branch prediction, NoC), coordination between architecture/system and workload (resource allocation and management, data center management, and security), compiler, and design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community.
Unsupervised aspect detection (UAD) aims at automatically extracting interpretable aspects and identifying aspect-specific segments (such as sentences) from online reviews. However, recent deep learning-based topic models, specifically aspect-based autoencoder, suffer from several problems, such as extracting noisy aspects and poorly mapping aspects discovered by models to the aspects of interest. To tackle these challenges, in this paper, we first propose a self-supervised contrastive learning framework and an attention-based model equipped with a novel smooth self-attention (SSA) module for the UAD task in order to learn better representations for aspects and review segments. Secondly, we introduce a high-resolution selective mapping (HRSMap) method to efficiently assign aspects discovered by the model to aspects of interest. We also propose using a knowledge distilling technique to further improve the aspect detection performance. Our methods outperform several recent unsupervised and weakly supervised approaches on publicly available benchmark user review datasets. Aspect interpretation results show that extracted aspects are meaningful, have good coverage, and can be easily mapped to aspects of interest. Ablation studies and attention weight visualization also demonstrate the effectiveness of SSA and the knowledge distilling method.
Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One of those deep learning-powered applications recently emerged is "deepfake". Deepfake algorithms can create fake images and videos that humans cannot distinguish them from authentic ones. The proposal of technologies that can automatically detect and assess the integrity of digital visual media is therefore indispensable. This paper presents a survey of algorithms used to create deepfakes and, more importantly, methods proposed to detect deepfakes in the literature to date. We present extensive discussions on challenges, research trends and directions related to deepfake technologies. By reviewing the background of deepfakes and state-of-the-art deepfake detection methods, this study provides a comprehensive overview of deepfake techniques and facilitates the development of new and more robust methods to deal with the increasingly challenging deepfakes.
Unmanned Aerial Vehicles are increasingly being used in surveillance and traffic monitoring thanks to their high mobility and ability to cover areas at different altitudes and locations. One of the major challenges is to use aerial images to accurately detect cars and count them in real-time for traffic monitoring purposes. Several deep learning techniques were recently proposed based on convolution neural network (CNN) for real-time classification and recognition in computer vision. However, their performance depends on the scenarios where they are used. In this paper, we investigate the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images. We trained and tested these two models on a large car dataset taken from UAVs. We demonstrated in this paper that YOLOv3 outperforms Faster R-CNN in sensitivity and processing time, although they are comparable in the precision metric.
Currently, the neural network architecture design is mostly guided by the \emph{indirect} metric of computation complexity, i.e., FLOPs. However, the \emph{direct} metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical \emph{guidelines} for efficient network design. Accordingly, a new architecture is presented, called \emph{ShuffleNet V2}. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.
Accurate Traffic Sign Detection (TSD) can help intelligent systems make better decisions according to the traffic regulations. TSD, regarded as a typical small object detection problem in some way, is fundamental in Advanced Driver Assistance Systems (ADAS) and self-driving. However, although deep neural networks have achieved human even superhuman performance on several tasks, due to their own limitations, small object detection is still an open question. In this paper, we proposed a brain-inspired network, named as KB-RANN, to handle this problem. Attention mechanism is an essential function of our brain, we used a novel recurrent attentive neural network to improve the detection accuracy in a fine-grained manner. Further, we combined domain specific knowledge and intuitive knowledge to improve the efficiency. Experimental result shows that our methods achieved better performance than several popular methods widely used in object detection. More significantly, we transplanted our method on our designed embedded system and deployed on our self-driving car successfully.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191