The digitisation of industry provides a plethora of novel applications that increase flexibility and reduce setup and maintenance time as well as cost. Furthermore, novel use cases are created by the digitisation of industry, commonly known as Industry 4.0 or the Industrial Internet of Things, applications make use of communication and computation technology that is becoming available. This enables novel business use cases, such as the digital twin, customer individual production, and data market places. However, the inter-connectivity such use cases rely on also significantly increases the attack surface of industrial enterprises. Sabotage and espionage are aimed at data, which is becoming the most crucial asset of an enterprise. Since the requirements on security solutions in industrial networks are inherently different from office networks, novel approaches for intrusion detection need to be developed. In this work, process data of a real water treatment process that contains attacks is analysed. Analysis is performed by an extension of Matrix Profiles, a motif discovery algorithm for time series. By extending Matrix Profiles with a Hammingdistance metric, binary and tertiary actuators can be integrated into the analysis in a meaningful fashion. This algorithm requires low training effort while providing accurate results. Furthermore, it can be employed in a real-time fashion. Selected actuators in the data set are analysed to highlight the applicability of the extended Matrix Profiles.
There are hardly any data sets publicly available that can be used to evaluate intrusion detection algorithms. The biggest threat for industrial applications arises from state-sponsored and criminal groups. Often, formerly unknown exploits are employed by these attackers, so-called 0-day exploits. They cannot be discovered with signature-based intrusion detection. Thus, statistical or machine learning based anomaly detection lends itself readily. These methods especially, however, need a large amount of labelled training data. In this work, an exemplary industrial use case with real-world indu…
The advanced development of the Internet facilitates efficient information exchange while also been exploited by adversaries. Intrusion detection system (IDS) as an important defense component of network security has always been widely studied in security research. However, research on intrusion prediction, which is more critical for network security, is received less attention. We argue that the advanced anticipation and timely impede of invasion is more vital than simple alarms in security defenses. General research methods regarding prediction are analyzing short term of system-calls to pre…
A Survey for Deep Reinforcement Learning Based Network Intrusion Detection
Department of Computer Sciences, University of Liverpool（计算机科学系，利物浦大学）；Centre for Doctoral Training (CDT) in Distributed Algorithm, University of Liverpool（分布式算法博士培训中心，利物浦大学）；Department of Electrical Engineering and Electronics, University of Liverpool（电子工程与电子系，利物浦大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）
Software-defined networking (SDN) was devised to simplify network management and automate infrastructure sharing in wired networks. These benefits motivated the application of SDN in wireless sensor networks to leverage solutions for complex applications. However, some of the core SDN traits turn the networks prone to denial of service attacks (DoS). There are proposals in the literature to detect DoS in wireless SDN networks, however, not without shortcomings: there is little focus on resource constraints, high detection rates have been reported only for small networks, and the detection is d…
Gated Recurrent Unit (GRU) is a recently-developed variation of the long short-term memory (LSTM) unit, both of which are types of recurrent neural network (RNN). Through empirical evidence, both models have been proven to be effective in a wide variety of machine learning tasks such as natural language processing (Wen et al., 2015), speech recognition (Chorowski et al., 2015), and text classification (Yang et al., 2016). Conventionally, like most neural networks, both of the aforementioned RNN variants employ the Softmax function as its final output layer for its prediction, and the cross-ent…
Timestamp-Aware Spatio-Temporal Graph Contrastive Learning for Network Intrusion Detection
Central South University of Forestry and Technology, School of Computer Science and Mathematics（中央林业科技大学计算机科学与数学学院）；Central South University, School of Computer Science and Engineering（中南大学计算机科学与工程学院）
Beihang University（北京航空航天大学）；Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University（北京航空航天大学大数据与脑计算高精尖创新中心）
Detecting the newly emerging malware variants in real time is crucial for mitigating cyber risks and proactively blocking intrusions. In this paper, we propose MG-DVD, a novel detection framework based on dynamic heterogeneous graph learning, to detect malware variants in real time. Particularly, MG-DVD first models the fine-grained execution event streams of malware variants into dynamic heterogeneous graphs and investigates real-world meta-graphs between malware objects, which can effectively characterize more discriminative malicious evolutionary patterns between malware and their variants.…
RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework
Department of Computer Science（计算机科学系）；Tennessee Tech University（田纳西科技大学）；School of Interdisciplinary Informatics（跨学科信息学学院）；University of Nebraska Omaha（内布拉斯加大学奥马哈分校）
