scispace - formally typeset
Search or ask a question
Author

Diane Gan

Bio: Diane Gan is an academic researcher from University of Greenwich. The author has contributed to research in topics: Malware & Intrusion detection system. The author has an hindex of 12, co-authored 37 publications receiving 480 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: A mathematical model is developed to determine when computation offloading is beneficial given parameters related to the operation of the network and the processing demands of the deep learning model, and the more reliable the network, the greater the reduction in detection latency achieved through offloading.
Abstract: Detection of cyber attacks against vehicles is of growing interest. As vehicles typically afford limited processing resources, proposed solutions are rule-based or lightweight machine learning techniques. We argue that this limitation can be lifted with computational offloading commonly used for resource-constrained mobile devices. The increased processing resources available in this manner allow access to more advanced techniques. Using as case study a small four-wheel robotic land vehicle, we demonstrate the practicality and benefits of offloading the continuous task of intrusion detection that is based on deep learning. This approach achieves high accuracy much more consistently than with standard machine learning techniques and is not limited to a single type of attack or the in-vehicle CAN bus as previous work. As input, it uses data captured in real-time that relate to both cyber and physical processes, which it feeds as time series data to a neural network architecture. We use both a deep multilayer perceptron and recurrent neural network architecture, with the latter benefitting from a long-short term memory hidden layer, which proves very useful for learning the temporal context of different attacks. We employ denial of service, command injection and malware as examples of cyber attacks that are meaningful for a robotic vehicle. The practicality of computation offloading depends on the resources afforded onboard and remotely, and the reliability of the communication means between them. Using detection latency as the criterion, we have developed a mathematical model to determine when computation offloading is beneficial given parameters related to the operation of the network and the processing demands of the deep learning model. The more reliable the network and the greater the processing demands, the greater the reduction in detection latency achieved through offloading.

186 citations

Proceedings ArticleDOI
16 Nov 2015
TL;DR: This work has developed an intrusion detection system that takes into account not only cyber input features, such as network traffic and disk data, but also physical input features such as speed, physical jittering and power consumption, which can markedly reduce the false positive rate and increase the overall accuracy of the detection.
Abstract: Mobile cyber-physical systems, such as automobiles, drones and robotic vehicles, are gradually becoming attractive targets for cyber attacks This is a challenge because intrusion detection systems built for conventional computer systems tend to be unsuitable They can be too demanding for resource-restricted cyber-physical systems or too inaccurate due to the lack of real-world data on actual attack behaviours Here, we focus on the security of a small remote-controlled robotic vehicle Having observed that certain types of cyber attacks against it exhibit physical impact, we have developed an intrusion detection system that takes into account not only cyber input features, such as network traffic and disk data, but also physical input features, such as speed, physical jittering and power consumption As the system is resource-restricted, we have opted for a decision tree-based approach for generating simple detection rules, which we evaluate against denial of service and command injection attacks We observe that the addition of physical input features can markedly reduce the false positive rate and increase the overall accuracy of the detection

64 citations

Journal ArticleDOI
TL;DR: It is observed that security training makes a noticeable difference in a user's ability to detect deception attempts, with one of the most important features being the time since last self-study, while formal security education through lectures appears to be much less useful as a predictor.
Abstract: Semantic social engineering attacks are a pervasive threat to computer and communication systems. By employing deception rather than by exploiting technical vulnerabilities, spear-phishing, obfuscated URLs, drive-by downloads, spoofed websites, scareware, and other attacks are able to circumvent traditional technical security controls and target the user directly. Our aim is to explore the feasibility of predicting user susceptibility to deception-based attacks through attributes that can be measured, preferably in real-time and in an automated manner. Toward this goal, we have conducted two experiments, the first on 4333 users recruited on the Internet, allowing us to identify useful high-level features through association rule mining, and the second on a smaller group of 315 users, allowing us to study these features in more detail. In both experiments, participants were presented with attack and non-attack exhibits and were tested in terms of their ability to distinguish between the two. Using the data collected, we have determined practical predictors of users’ susceptibility against semantic attacks to produce and evaluate a logistic regression and a random forest prediction model, with the accuracy rates of. 68 and. 71, respectively. We have observed that security training makes a noticeable difference in a user’s ability to detect deception attempts, with one of the most important features being the time since last self-study, while formal security education through lectures appears to be much less useful as a predictor. Other important features were computer literacy, familiarity, and frequency of access to a specific platform. Depending on an organisation’s preferences, the models learned can be configured to minimise false positives or false negatives or maximise accuracy, based on a probability threshold. For both models, a threshold choice of 0.55 would keep both false positives and false negatives below 0.2.

57 citations

Proceedings ArticleDOI
28 Dec 2015
TL;DR: A decision tree-based method for detecting cyber attacks on a small-scale robotic vehicle using both cyber and physical features that can be measured by its on-board systems and processes that noticeably improves the detection accuracy for two of the four attack types and reduces the detection latency for all four.
Abstract: Intrusion detection systems designed for conventional computer systems and networks are not necessarily suitable for mobile cyber-physical systems, such as robots, drones and automobiles. They tend to be geared towards attacks of different nature and do not take into account mobility, energy consumption and other physical aspects that are vital to a mobile cyber-physical system. We have developed a decision tree-based method for detecting cyber attacks on a small-scale robotic vehicle using both cyber and physical features that can be measured by its on-board systems and processes. We evaluate it experimentally against a variety of scenarios involving denial of service, command injection and two types of malware attacks. We observe that the addition of physical features noticeably improves the detection accuracy for two of the four attack types and reduces the detection latency for all four.

45 citations

Proceedings ArticleDOI
01 Dec 2016
TL;DR: A detection mechanism, which monitors real-time data from a large number of sources onboard the vehicle, including its sensors, networks and processing, and approach the problem as a binary classification problem of whether the robot is able to self-detect when and whether it is under attack.
Abstract: Security is one of the key challenges in cyberphysical systems, because by their nature, any cyber attack against them can have physical repercussions. This is a critical issue for autonomous vehicles; if compromised in terms of their communications or computation they can cause considerable physical damage due to their mobility. Our aim here is to facilitate the automatic detection of cyber attacks on a robotic vehicle. For this purpose, we have developed a detection mechanism, which monitors real-time data from a large number of sources onboard the vehicle, including its sensors, networks and processing. Following a learning phase, where the vehicle is trained in a non-attack state on what values are considered normal, it is then subjected to a series of different cyber-physical and physical-cyber attacks. We approach the problem as a binary classification problem of whether the robot is able to self-detect when and whether it is under attack. Our experimental results show that the approach is promising for most attacks that the vehicle is subjected to. We further improve its performance by using weights that accentuate the anomalies that are less common thus improving overall performance of the detection mechanism for unknown attacks.

39 citations


Cited by
More filters
Journal ArticleDOI
01 Feb 2020
TL;DR: A survey of deep learning approaches for cyber security intrusion detection, the datasets used, and a comparative study to evaluate the efficiency of several methods are presented.
Abstract: In this paper, we present a survey of deep learning approaches for cybersecurity intrusion detection, the datasets used, and a comparative study. Specifically, we provide a review of intrusion detection systems based on deep learning approaches. The dataset plays an important role in intrusion detection, therefore we describe 35 well-known cyber datasets and provide a classification of these datasets into seven categories; namely, network traffic-based dataset, electrical network-based dataset, internet traffic-based dataset, virtual private network-based dataset, android apps-based dataset, IoT traffic-based dataset, and internet-connected devices-based dataset. We analyze seven deep learning models including recurrent neural networks, deep neural networks, restricted Boltzmann machines, deep belief networks, convolutional neural networks, deep Boltzmann machines, and deep autoencoders. For each model, we study the performance in two categories of classification (binary and multiclass) under two new real traffic datasets, namely, the CSE-CIC-IDS2018 dataset and the Bot-IoT dataset. In addition, we use the most important performance indicators, namely, accuracy, false alarm rate, and detection rate for evaluating the efficiency of several methods.

464 citations

Journal ArticleDOI
TL;DR: This survey paper describes a literature review of deep learning methods for cyber security applications, including deep autoencoders, restricted Boltzmann machines, recurrent neural networks, generative adversarial networks, and several others.
Abstract: This survey paper describes a literature review of deep learning (DL) methods for cyber security applications. A short tutorial-style description of each DL method is provided, including deep autoencoders, restricted Boltzmann machines, recurrent neural networks, generative adversarial networks, and several others. Then we discuss how each of the DL methods is used for security applications. We cover a broad array of attack types including malware, spam, insider threats, network intrusions, false data injection, and malicious domain names used by botnets.

343 citations

Journal ArticleDOI
TL;DR: This survey discusses the role of deep learning in intrusion detection, the impact of intrusion detection datasets, and the efficiency and effectiveness of the proposed approaches, and provides a novel fine-grained taxonomy that categorizes the current state-of-the-art deep learning-based IDSs with respect to different facets.
Abstract: The massive growth of data that are transmitted through a variety of devices and communication protocols have raised serious security concerns, which have increased the importance of developing advanced intrusion detection systems (IDSs). Deep learning is an advanced branch of machine learning, composed of multiple layers of neurons that represent the learning process. Deep learning can cope with large-scale data and has shown success in different fields. Therefore, researchers have paid more attention to investigating deep learning for intrusion detection. This survey comprehensively reviews and compares the key previous deep learning-focused cybersecurity surveys. Through an extensive review, this survey provides a novel fine-grained taxonomy that categorizes the current state-of-the-art deep learning-based IDSs with respect to different facets, including input data, detection, deployment, and evaluation strategies. Each facet is further classified according to different criteria. This survey also compares and discusses the related experimental solutions proposed as deep learning-based IDSs. By analysing the experimental studies, this survey discusses the role of deep learning in intrusion detection, the impact of intrusion detection datasets, and the efficiency and effectiveness of the proposed approaches. The findings demonstrate that further effort is required to improve the current state-of-the art. Finally, open research challenges are identified, and future research directions for deep learning-based IDSs are recommended.

283 citations

Journal ArticleDOI
TL;DR: An extensive set of technical challenges are enumerated and specific applications are used to elaborate and provide insight into each specific concept in the Cyber-Physical System.
Abstract: The Cyber-Physical System (CPS) is a term describing a broad range of complex, multi-disciplinary, physically-aware next generation engineered system that integrates embedded computing technologies (cyber part) into the physical world. In order to define and understand CPS more precisely, this article presents a detailed survey of the related work, discussing the origin of CPS, the relations to other research fields, prevalent concepts, and practical applications. Further, this article enumerates an extensive set of technical challenges and uses specific applications to elaborate and provide insight into each specific concept. CPS is a very broad research area and therefore has diverse applications spanning different scales. Additionally, the next generation technologies are expected to play an important role on CPS research. All of CPS applications need to be designed considering the cutting-edge technologies, necessary system-level requirements, and overall impact on the real world.

263 citations

Journal ArticleDOI
TL;DR: A mathematical model is developed to determine when computation offloading is beneficial given parameters related to the operation of the network and the processing demands of the deep learning model, and the more reliable the network, the greater the reduction in detection latency achieved through offloading.
Abstract: Detection of cyber attacks against vehicles is of growing interest. As vehicles typically afford limited processing resources, proposed solutions are rule-based or lightweight machine learning techniques. We argue that this limitation can be lifted with computational offloading commonly used for resource-constrained mobile devices. The increased processing resources available in this manner allow access to more advanced techniques. Using as case study a small four-wheel robotic land vehicle, we demonstrate the practicality and benefits of offloading the continuous task of intrusion detection that is based on deep learning. This approach achieves high accuracy much more consistently than with standard machine learning techniques and is not limited to a single type of attack or the in-vehicle CAN bus as previous work. As input, it uses data captured in real-time that relate to both cyber and physical processes, which it feeds as time series data to a neural network architecture. We use both a deep multilayer perceptron and recurrent neural network architecture, with the latter benefitting from a long-short term memory hidden layer, which proves very useful for learning the temporal context of different attacks. We employ denial of service, command injection and malware as examples of cyber attacks that are meaningful for a robotic vehicle. The practicality of computation offloading depends on the resources afforded onboard and remotely, and the reliability of the communication means between them. Using detection latency as the criterion, we have developed a mathematical model to determine when computation offloading is beneficial given parameters related to the operation of the network and the processing demands of the deep learning model. The more reliable the network and the greater the processing demands, the greater the reduction in detection latency achieved through offloading.

186 citations