Forensics and Deep Learning Mechanisms for Botnets in Internet of Things: A Survey of Challenges and Solutions

Koroniotis, Nickolaos; Moustafa, Nour; Sitnikova, Elena

doi:10.1109/access.2019.2916717

Cited by 113 publications

(70 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Even though many forensic frameworks have been proposed [12,27,11], existing solutions for smart homes give emphasis on acquisition and neglect examination and analysis. Furthermore, no single framework has been acknowledged as superior, due to lack of standardization in IoT and heterogeneity of computer systems [28,29,3].…”

Section: Digital Forensicsmentioning

confidence: 99%

“…In a 2018 report by Symantec regarding the security threats found in the Internet [2], it was reported that the total number of attacks targeting IoT devices for 2018 exceeded 57,000, with more than 5,000 attacks being recorded each month. Hackers have compromised vulnerable, unpatched or unencrypted IoT devices in order to steal sensitive data, corrupt the device's normal operation, spread malware infections [3][4] [2] or even compromise the security of a smart home by disabling smart locks and garage doors [5].…”

Section: Introductionmentioning

confidence: 99%

“…Due to the lack of common standards and heterogeneity displayed by the IoT [3], the development of an efficient network forensic solution becomes difficult [6], as there may be multiple diverse protocols in use in a single deployment [7][8][9]. Typically, the network forensic process is segmented into several distinct phases, whereby each phase defines the necessary preparation, analysis and actions of investigation [10], with these phases being identification, collection, preservation, examination, analysis and presentation.…”

Section: Introductionmentioning

confidence: 99%

“…Network flow analysis summarizes network traffic, by ignoring the payload and utilising statistical data like connection speed and exchanged bits. For the requirements of the research presented in this paper, network flow is preferred, as we suggest in this work [3].…”

Section: Introductionmentioning

confidence: 99%

“…Regardless, no single optimization method has been accepted as the preferred method by the research community and as such, the research is ongoing. It is a necessity to develop network forensic-based optimisation to timely investigate security incidents in IoT networks [23,3,24] .…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Koroniotis

Moustafa

2020

7th International Conference on Artificial Intelligence and Applications

Self Cite

View full text Add to dashboard Cite

The popularity of IoT smart things is rising, due to the automation they provide and its effects on productivity. However, it has been proven that IoT devices are vulnerable to both well established and new IoT-specific attack vectors. In this paper, we propose the Particle Deep Framework, a new network forensic framework for IoT networks that utilised Particle Swarm Optimisation to tune the hyperparameters of a deep MLP model and improve its performance. The PDF is trained and validated using Bot-IoT dataset, a contemporary network-traffic dataset that combines normal IoT and non-IoT traffic, with well known botnet-related attacks. Through experimentation, we show that the performance of a deep MLP model is vastly improved, achieving an accuracy of 99.9% and false alarm rate of close to 0%.

show abstract

Section: Digital Forensicsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Koroniotis

Moustafa

2020

7th International Conference on Artificial Intelligence and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

Advanced Attacks and Protection Mechanisms in IoT Devices and Networks

Batina

Mentens

Miettinen

et al. 2021

Security and Privacy in the Internet of Things

View full text Add to dashboard Cite

ANGUISH: Security attack in narrowband‐Internet of Things (NB‐IoT) using game theory and hardware analysis

Kumar

Jha

Jain

2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In recent years, the Internet of Things (IoT) plays a vital role in our daily life.IoT is dominating in many areas like industries, health care, smart home, social network, defense sector, and the education sector. In the last couple of years, users are facing different challenges like security issues related to social network and defense sector. In this article, our prime focus is to secure the social and defense network associated with narrowband-Internet of Things. This article proposes the artificial intelligence (AI)-based defense security attacks using unmanned aerial vehicle (UAV). In the first part of the article, we have proposed attack modeling on smart home scenario and finalize the critical parameter for performance analysis. In the next section, the performance analysis based on game theory (GT) (AI based) approach is attained, using different techniques like nash equilibrium and Prisoner's dilemma. In the last section, detailed hardware analysis has been carried out for analyzing attack in real-time scenario and is illustrated with the help of step-by-step process. Our proposed model proves that UAV-based router can spoof by the intruder with the probability of 0.4 using GT and hardware analysis. INTRODUCTIONThe evolution of IoT started with radio frequency identification (RFID), which is vastly used in various applications like supply chain management, object tracking, and asset tracking. Other than RFID, wireless sensor network (WSN), machine to machine (M2M), software-defined networking (SDN), supervisory control and data acquisition (SCADA), cloud computing, and embedded computing are numerous technologies that also support the IoT. All these technologies are used for the different applications of IoT, such as smart homes, smart cities, smart grid, wearables, connected healthcare, smart agriculture, industrial Internet, and connected car. The advancement in IoT has different challenges like energy efficiency, spectrum utilization, a massive amount of sensors generated data, device heterogeneity, and data security. The usage of energy-efficient, low power wide area network (LPWAN) radio technologies is increasing gradually. These technologies are licensed as well as unlicensed. Unlicensed spectrum technologies such as long range (LoRa), INGENU, and SIGFOX, while licensed spectrum consists of long-term evolution-machine-type communication s(LTE-M), and NB-IoT. NB-IoT is the energy-efficient technology standard defined by 3rd Generation Partnership Project (3GPP) in release 13. It fulfills the critical requirement of IoT like low-device complexity, extended battery lifetime, deep indoor coverage, and a massive number of two-way communication of device support per cell. 1 NB-IoT is used to achieve the outstanding performance of GSM and LTE technologies and entails a minimum of 180 kHz system bandwidth for both downlink and uplink channel. 2 The uplink communication channel uses single-carrier frequency division Trans Emerging Tel Tech.

show abstract

Forensics and Deep Learning Mechanisms for Botnets in Internet of Things: A Survey of Challenges and Solutions

Abstract: The author N. Koroniotis would like to thank the Commonwealth's support, which is provided to the aforementioned researcher in the form of an Australian Government Research Training Program Scholarship.

Cited by 113 publications

References 84 publications

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Advanced Attacks and Protection Mechanisms in IoT Devices and Networks

ANGUISH: Security attack in narrowband‐Internet of Things (NB‐IoT) using game theory and hardware analysis

Contact Info

Product

Resources

About