Micromovement Behavior as an Intention Detection Measurement for Preventing Insider Threats

Almehmadi, Abdulaziz

doi:10.1109/access.2018.2857450

Cited by 22 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since digital assets are of great importance, as their integrity is essential to the success of organizations, some organizations implemented various measures to mitigate insider threats, such as employees vetting, authentication mechanisms, training, monitoring, separation of duty, etc. [6] However, due to an authorization characteristic that the insiders have, traditional measures are effective to detect insider threats and mitigate their impacts [7].…”

Section: Strategies For Insider Threat Detectionmentioning

confidence: 99%

An Insider Data Leakage Detection Using One-Hot Encoding, Synthetic Minority Oversampling and Machine Learning Techniques

Al-Shehari

Alsowail

2021

Entropy

106

View full text Add to dashboard Cite

Insider threats are malicious acts that can be carried out by an authorized employee within an organization. Insider threats represent a major cybersecurity challenge for private and public organizations, as an insider attack can cause extensive damage to organization assets much more than external attacks. Most existing approaches in the field of insider threat focused on detecting general insider attack scenarios. However, insider attacks can be carried out in different ways, and the most dangerous one is a data leakage attack that can be executed by a malicious insider before his/her leaving an organization. This paper proposes a machine learning-based model for detecting such serious insider threat incidents. The proposed model addresses the possible bias of detection results that can occur due to an inappropriate encoding process by employing the feature scaling and one-hot encoding techniques. Furthermore, the imbalance issue of the utilized dataset is also addressed utilizing the synthetic minority oversampling technique (SMOTE). Well known machine learning algorithms are employed to detect the most accurate classifier that can detect data leakage events executed by malicious insiders during the sensitive period before they leave an organization. We provide a proof of concept for our model by applying it on CMU-CERT Insider Threat Dataset and comparing its performance with the ground truth. The experimental results show that our model detects insider data leakage events with an AUC-ROC value of 0.99, outperforming the existing approaches that are validated on the same dataset. The proposed model provides effective methods to address possible bias and class imbalance issues for the aim of devising an effective insider data leakage detection system.

show abstract

Section: Strategies For Insider Threat Detectionmentioning

confidence: 99%

An Insider Data Leakage Detection Using One-Hot Encoding, Synthetic Minority Oversampling and Machine Learning Techniques

Al-Shehari

Alsowail

2021

Entropy

106

View full text Add to dashboard Cite

show abstract

“…Some areas of research look at human behavior as a potential threat. The authors in [16] detected head micro-movement behavior in response to text and images that related to information stored in subjects' brains to infer if the information was stored in the brain relying on the fight, flight, or freeze response [17]. Behavior-based surveillance systems have also evolved to detect general anomalies in public.…”

Section: B) Behavior-based Detectionmentioning

confidence: 99%

Synchronous Head Movement as a Crowd-Behavior-Based Security System

Almehmadi

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Individuals react in response to internal or external stimuli, whether visual, auditory, gustatory, olfactory, cutaneous, kinesthetic, or vestibular. This behavior is not fully utilized to infer possible security incidents taking place or about to take place in a defined geographical area outside of the range or field-ofview of security systems. Sensors are in place in the form of human senses. If these natural sensors are utilized together with advances in deep learning technology, researchers will be equipped to build advanced security solutions. In this paper, we propose a security system based on the crowd behavior of synchronous head movement (SHMOV). The system provides an alert of a possible security incident if synchronous head movement occurs among a crowd in a specific area by analyzing the video stream from a camera. We assessed the proposed SHMOV system using an experiment on 20 participants in auditory, visual, and olfactory settings. This experiment demonstrated the technology's potential, with 100%, 100%, and 80% incident detection accuracy and alerts issued 9, 24, and 47 seconds after the start of each incident, respectively.

show abstract

“…The authors in [21] further proposed a novel system and patent [22] to examine the usage of head micromovement to detect malicious intent using visual stimuli and reported an accuracy of 100% intention detection with a lower accuracy (70%) in motivation detection compared with the analysis of EEG signals to detect a user's motivation for an intended action.…”

Section: Intentional-based Human Errormentioning

confidence: 99%

Micro-Behavioral Accidental Click Detection System for Preventing Slip-Based Human Error

Almehmadi¹

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Accidentally clicking on a link is a type of human error known as a slip in which a user unintentionally performs an unintended task. The risk magnitude is the probability of occurrences of such error with a possible substantial effect to which even experienced individuals are susceptible. Phishing attacks take advantage of slip-based human error by attacking psychological aspects of the users that lead to unintentionally clicking on phishing links. Such actions may lead to installing tracking software, downloading malware or viruses, or stealing private, sensitive information, to list a few. Therefore, a system is needed that detects whether a click on a link is intentional or unintentional and, if unintentional, can then prevent it. This paper proposes a micro-behavioral accidental click detection system (ACDS) to prevent slip-based human error. A within-subject-based experiment was conducted with 20 participants to test the potential of the proposed system. The results reveal the statistical significance between the two cases of intentional vs. unintentional clicks using a smartphone. Random tree, random forest, and support vector machine classifiers were used, exhibiting 82.6%, 87.2%, and 91.6% accuracy in detecting unintentional clicks, respectively.

show abstract

Micromovement Behavior as an Intention Detection Measurement for Preventing Insider Threats

Cited by 22 publications

References 19 publications

An Insider Data Leakage Detection Using One-Hot Encoding, Synthetic Minority Oversampling and Machine Learning Techniques

An Insider Data Leakage Detection Using One-Hot Encoding, Synthetic Minority Oversampling and Machine Learning Techniques

Synchronous Head Movement as a Crowd-Behavior-Based Security System

Micro-Behavioral Accidental Click Detection System for Preventing Slip-Based Human Error

Contact Info

Product

Resources

About