A Multi-Modal Neuro-Physiological Study of Malicious Insider Threats

Hashem, Yassir; Takabi, Hassan; Dantu, Ram; Nielsen, Rodney D.

doi:10.1145/3139923.3139930

Cited by 8 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The varSelRF and Boruta algorithms achieved similar performances. 2017) did because they distinguished the types of scenario that the subjects faced [51]. They tried to classify different kinds of tasks, while we tried to classify two kinds of scenarios with similar structures and lengths.…”

Section: Resultsmentioning

confidence: 99%

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

Kim

Yim

2020

Sensors

View full text Add to dashboard Cite

This study proposes a scheme to identify insider threats in nuclear facilities through the detection of malicious intentions of potential insiders using subject-wise classification. Based on electroencephalography (EEG) signals, a classification model was developed to identify whether a subject has a malicious intention under scenarios of being forced to become an insider threat. The model also distinguishes insider threat scenarios from everyday conflict scenarios. To support model development, 21-channel EEG signals were measured on 25 healthy subjects, and sets of features were extracted from the time, time–frequency, frequency and nonlinear domains. To select the best use of the available features, automatic selection was performed by random-forest-based algorithms. The k-nearest neighbor, support vector machine with radial kernel, naïve Bayes, and multilayer perceptron algorithms were applied for the classification. By using EEG signals obtained while contemplating becoming an insider threat, the subject-wise model identified malicious intentions with 78.57% accuracy. The model also distinguished insider threat scenarios from everyday conflict scenarios with 93.47% accuracy. These findings could be utilized to support the development of insider threat mitigation systems along with existing trustworthiness assessments in the nuclear industry.

show abstract

Section: Resultsmentioning

confidence: 99%

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

Kim

Yim

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…They extracted features from those signals and used them to train classifiers, such as support vector machine (SVM), k-nearest neighbor (KNN), and random forest (RF), to distinguish between anomalous and benign activities. Both experimental results showed that EEG signals can reveal valuable information about a user's malicious intent and can be used as an effective indicator in designing real-time insider threat monitoring and detection frameworks [ 25 ].…”

Section: Related Workmentioning

confidence: 96%

“…A body of research has focused on detecting anomalous behaviors in some interesting ways. References [ 25 ] and [ 26 ] conducted multimodel neurophysiological assessments to learn how users' brains act when the user is performing abnormal and normal activities. In particular, they focused on using electroencephalogram (EEG) signals that arise from the user's brain activities and eye tracking, which can capture spontaneous responses that are unfiltered by the conscious mind [ 25 ].…”

Section: Related Workmentioning

confidence: 99%

“…References [ 25 ] and [ 26 ] conducted multimodel neurophysiological assessments to learn how users' brains act when the user is performing abnormal and normal activities. In particular, they focused on using electroencephalogram (EEG) signals that arise from the user's brain activities and eye tracking, which can capture spontaneous responses that are unfiltered by the conscious mind [ 25 ]. They extracted features from those signals and used them to train classifiers, such as support vector machine (SVM), k-nearest neighbor (KNN), and random forest (RF), to distinguish between anomalous and benign activities.…”

Section: Related Workmentioning

confidence: 99%

“…It was reported that 53 percent of organizations encountered an attack from insiders, 27 percent thought that attacks from insiders were more frequent, and 90 percent admitted that they were unable to defend against insider threats. Furthermore, just last year, a report from the Ponemon Institute studied cyberattack cases for over 237 companies in six countries around the world and found that insider threat was the most expensive attack, costing companies an average of $167,890 annually, and this cost is likely to increase in the future [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

User and Entity Behavior Analysis under Urban Big Data

Tian¹,

Luo

Lu³

et al. 2020

ACM/IMS Trans. Data Sci.

View full text Add to dashboard Cite

Recently, the urban network infrastructure has undergone a rapid expansion that is increasingly generating a large quantity of data and transforming our cities into smart cities. However, serious security problems arise with this development with more and more smart devices collecting private information under smart city scenario. In this article, we investigate the task of detecting insiders' anomalous behaviors to prevent urban big data leakage. Specifically, we characterize a user's daily activities from four perspectives and use several deep learning algorithms (long short-term memory (LSTM) and convolutional LSTM (convLSTM)) to calculate deviations between realistic actions and normalcy of daily behaviors and use multilayer perceptron (MLP) to identify abnormal behaviors according to those deviations. To evaluate the proposed multimodelbased system (MBS), we conducted experiments on the CERT (United States Computer Emergency Readiness Team) dataset. The experimental results show that our proposed MBS has a remarkable ability to learn the normal pattern of users' daily activities and detect anomalous behaviors.

show abstract

A systematic review and research challenges on phishing cyberattacks from an electroencephalography and gaze-based perspective

Thomopoulos,

Lyras,

Fidas

2024

Pers Ubiquit Comput

View full text Add to dashboard Cite

Phishing is one of the most important security threats in modern information systems causing different levels of damages to end-users and service providers such as financial and reputational losses. State-of-the-art anti-phishing research is highly fragmented and monolithic and does not address the problem from a pervasive computing perspective. In this survey, we aim to contribute to the existing literature by providing a systematic review of existing experimental phishing research that employs EEG and eye-tracking methods within multi-modal and multi-sensory interaction environments. The main research objective of this review is to examine articles that contain results of at least one EEG-based and/or eye-tracking-based experimental setup within a phishing context. The database search with specific search criteria yielded 651 articles from which, after the identification and the screening process, 42 articles were examined as per the execution of experiments using EEG or eye-tracking technologies in the context of phishing, resulting to a total of 18 distinct papers that were included in the analysis. This survey is approaching the subject across the following pillars: a) the experimental design practices with an emphasis on the applied EEG and eye-tracking acquisition protocols, b) the artificial intelligence and signal preprocessing techniques that were applied in those experiments, and finally, c) the phishing attack types examined. We also provide a roadmap for future research in the field by suggesting ideas on how to combine state-of-the-art gaze-based mechanisms with EEG technologies for advancing phishing research. This leads to a discussion on the best practices for designing EEG and gaze-based frameworks.

show abstract

A Multi-Modal Neuro-Physiological Study of Malicious Insider Threats

Cited by 8 publications

References 29 publications

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

User and Entity Behavior Analysis under Urban Big Data

A systematic review and research challenges on phishing cyberattacks from an electroencephalography and gaze-based perspective

Contact Info

Product

Resources

About