scholarly journals Endpoint detection and response using machine learning

2021 ◽  
Vol 2062 (1) ◽  
pp. 012013
Author(s):  
Harmionee Kaur ◽  
Richa Tiwari
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection Systems ◽  
Endpoint Detection ◽  
Detection Systems ◽  
The Past ◽  
Iot Devices

Abstract The need for cybersecurity has increased manifold over the past decade due to an unprecedented shift towards digital. With the increase in the number and sophistication of threats, cybersecurity experts have been forced to seek out new and efficient ways to secure endpoints on a network. Machine learning provides one such solution. This paper discusses how IoT devices are threatened and the need for endpoint security. It overviews different Machine learning-based intrusion detection systems that are currently in use e.g., STAT, Haystack, etc., and other Endpoint Detection and Response Techniques.

scholarly journals Launching Adversarial Attacks against Network Intrusion Detection Systems for IoT

2021 ◽  
Vol 1 (2) ◽  
pp. 252-273
Author(s):  
Pavlos Papadopoulos ◽  
Oliver Thornewill von Essen ◽  
Nikolaos Pitropakis ◽  
Christos Chrysoulas ◽  
Alexios Mylonas ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection Systems ◽  
Learning Models ◽  
Detection Systems ◽  
Network Intrusion ◽  
Robust Model ◽  
Significant Probability ◽  
Adversarial Examples ◽  
Attack Surface

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought. Traditional defending approaches are no longer sufficient to detect both known and unknown attacks to high accuracy. Machine learning intrusion detection systems have proven their success in identifying unknown attacks with high precision. Nevertheless, machine learning models are also vulnerable to attacks. Adversarial examples can be used to evaluate the robustness of a designed model before it is deployed. Further, using adversarial examples is critical to creating a robust model designed for an adversarial environment. Our work evaluates both traditional machine learning and deep learning models’ robustness using the Bot-IoT dataset. Our methodology included two main approaches. First, label poisoning, used to cause incorrect classification by the model. Second, the fast gradient sign method, used to evade detection measures. The experiments demonstrated that an attacker could manipulate or circumvent detection with significant probability.

scholarly journals Recent Advancements in Intrusion Detection Systems for the Internet of Things

2019 ◽  
Vol 2019 ◽  
pp. 1-19 ◽  
Author(s):  
Zeeshan Ali Khan ◽  
Peter Herrmann
Keyword(s):  
Internet Of Things ◽  
Intrusion Detection ◽  
Ad Hoc ◽  
Denial Of Service ◽  
Research Work ◽  
Intrusion Detection Systems ◽  
Future Research ◽  
Detection Systems ◽  
Iot Applications ◽  
Iot Devices

Many Internet of Things (IoT) systems run on tiny connected devices that have to deal with severe processor and energy restrictions. Often, the limited processing resources do not allow the use of standard security mechanisms on the nodes, making IoT applications quite vulnerable to different types of attacks. This holds particularly for intrusion detection systems (IDS) that are usually too resource-heavy to be handled by small IoT devices. Thus, many IoT systems are not sufficiently protected against typical network attacks like Denial-of-Service (DoS) and routing attacks. On the other side, IDSs have already been successfully used in adjacent network types like Mobile Ad hoc Networks (MANET), Wireless Sensor Networks (WSN), and Cyber-Physical Systems (CPS) which, in part, face limitations similar to those of IoT applications. Moreover, there is research work ongoing that promises IDSs that may better fit to the limitations of IoT devices. In this article, we will give an overview about IDSs suited for IoT networks. Besides looking on approaches developed particularly for IoT, we introduce also work for the three similar network types mentioned above and discuss if they are also suitable for IoT systems. In addition, we present some suggestions for future research work that could be useful to make IoT networks more secure.

scholarly journals Ensemble-Based Online Machine Learning Algorithms for Network Intrusion Detection Systems Using Streaming Data

Information ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 315
Author(s):  
Nathan Martindale ◽  
Muhammad Ismail ◽  
Douglas A. Talbert
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Intrusion Detection ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Intrusion Detection Systems ◽  
Network Intrusion Detection ◽  
Detection Systems ◽  
Network Intrusion ◽  
Network Intrusion Detection Systems

As new cyberattacks are launched against systems and networks on a daily basis, the ability for network intrusion detection systems to operate efficiently in the big data era has become critically important, particularly as more low-power Internet-of-Things (IoT) devices enter the market. This has motivated research in applying machine learning algorithms that can operate on streams of data, trained online or “live” on only a small amount of data kept in memory at a time, as opposed to the more classical approaches that are trained solely offline on all of the data at once. In this context, one important concept from machine learning for improving detection performance is the idea of “ensembles”, where a collection of machine learning algorithms are combined to compensate for their individual limitations and produce an overall superior algorithm. Unfortunately, existing research lacks proper performance comparison between homogeneous and heterogeneous online ensembles. Hence, this paper investigates several homogeneous and heterogeneous ensembles, proposes three novel online heterogeneous ensembles for intrusion detection, and compares their performance accuracy, run-time complexity, and response to concept drifts. Out of the proposed novel online ensembles, the heterogeneous ensemble consisting of an adaptive random forest of Hoeffding Trees combined with a Hoeffding Adaptive Tree performed the best, by dealing with concept drift in the most effective way. While this scheme is less accurate than a larger size adaptive random forest, it offered a marginally better run-time, which is beneficial for online training.

Sign in / Sign up

Export Citation Format

Share Document