skip to main content

Title: Denial of Service (DoS) Attack Detection: Performance Comparison of Supervised Machine Learning Algorithms
Denial of Service (DoS) is one of the common attempts in security hacking for making computation resources unavailable or to impair geographical networks. In this paper, we detect Denial of Service (DoS) attack from publicly available datasets using Logistic regression, Naive Bayes algorithm and artificial neural networks. The results from our experiments indicate that the accuracy, ROC curve and balanced accuracy of artificial neural network were higher than Naive Bayes algorithm and logistic regression for slightly imbalanced distribution dataset.
Authors:
; ; ; ; ; ;
Award ID(s):
1723578
Publication Date:
NSF-PAR ID:
10273198
Journal Name:
Proc. of 18th IEEE International Conference on Dependable, Autonomic and Secure Computing (DASC)
Page Range or eLocation-ID:
469-474
Sponsoring Org:
National Science Foundation
More Like this
  1. Denial of Service (DoS) is one of the common attempts in security hacking for making computation resources unavailable or to impair geographical networks. In this paper, we detect Denial of Service (DoS) attack from publicly available datasets using Logistic regression, Naive Bayes algorithm and artificial neural networks. The results from our experiments indicate that the accuracy, ROC curve and balanced accuracy of artificial neural network were higher than Naive Bayes algorithm and logistic regression for slightly imbalanced distribution dataset.
  2. Unmanned aerial vehicles (UAVs) must keep track of their location in order to maintain flight plans. Currently, this task is almost entirely performed by a combination of Inertial Measurement Units (IMUs) and reference to GNSS (Global Navigation Satellite System). Navigation by GNSS, however, is not always reliable, due to various causes both natural (reflection and blockage from objects, technical fault, inclement weather) and artificial (GPS spoofing and denial). In such GPS-denied situations, it is desirable to have additional methods for aerial geolocalization. One such method is visual geolocalization, where aircraft use their ground facing cameras to localize and navigate. Themore »state of the art in many ground-level image processing tasks involve the use of Convolutional Neural Networks (CNNs). We present here a study of how effectively a modern CNN designed for visual classification can be applied to the problem of Absolute Visual Geolocalization (AVL, localization without a prior location estimate). An Xception based architecture is trained from scratch over a >1000 km2 section of Washington County, Arkansas to directly regress latitude and longitude from images from different orthorectified high-altitude survey flights. It achieves average localization accuracy on unseen image sets over the same region from different years and seasons with as low as 115 m average error, which localizes to 0.004% of the training area, or about 8% of the width of the 1.5 × 1.5 km input image. This demonstrates that CNNs are expressive enough to encode robust landscape information for geolocalization over large geographic areas. Furthermore, discussed are methods of providing uncertainty for CNN regression outputs, and future areas of potential improvement for use of deep neural networks in visual geolocalization.« less
  3. Modern vehicle is considered as a system vulnerable to attacks because it is connected to the outside world via a wireless interface. Although, connectivity provides more convenience and features to the passengers, however, it also becomes a pathway for the attackers targeting in-vehicle networks. Research in vehicle security is getting attention as in-vehicle attacks can impact human life safety as modern vehicle is connected to the outside world. Controller area network (CAN) is used as a legacy protocol for in-vehicle communication, However, CAN suffers from vulnerabilities due to lack of authentication, as the information about sender is missing in CANmore »message. In this paper, a new CAN intrusion detection system (IDS) is proposed, the CAN messages are converted to temporal graphs and CAN intrusion is detected using machine learning algorithms. Seven graph-based properties are extracted and used as features for detecting intrusions utilizing two machine learning algorithms which are support vector machine (SVM) & k-nearest neighbors (KNN). The performance of the IDS was evaluated over three CAN bus attacks are denial of service (DoS), fuzzy & spoofing attacks on real vehicular CAN bus dataset. The experimental results showed that using graph-based features, an accuracy of 97.92% & 97.99% was achieved using SVM & KNN algorithms respectively, which is better than using traditional machine learning CAN bus features.« less
  4. This paper presents a portable inertial measurement unit (IMU)-based motion sensing system and proposed an adaptive gait phase detection approach for non-steady state walking and multiple activities (walking, running, stair ascent, stair descent, squat) monitoring. The algorithm aims to overcome the limitation of existing gait detection methods that are time-domain thresholding based for steady-state motion and are not versatile to detect gait during different activities or different gait patterns of the same activity. The portable sensing suit is composed of three IMU sensors (wearable sensors for gait phase detection) and two footswitches (ground truth measurement and not needed for gaitmore »detection of the proposed algorithm). The acceleration, angular velocity, Euler angle, resultant acceleration, and resultant angular velocity from three IMUs are used as the input training data and the data of two footswitches used as the training label data (single support, double support, swing phase). Three methods 1) Logistic Regression (LR), 2) Random Forest Classifier (RF), and 3) Artificial Neural Network (NN) are used to build the gait phase detection models. The result shows our proposed gait phase detection with Random Forest Classifier can achieve 98.94% accuracy in walking, 98.45% in running, 99.15% in stair-ascent, 99.00% in stair-descent, and 99.63% in squatting. It demonstrates that our sensing suit can not only detect the gait status in any transient state but also generalize to multiple activities. Therefore, it can be implemented in real-time monitoring of human gait and control of assistive devices.« less
  5. Lighting, as a significant component of indoor environment quality, was found to be a primary contributor to deficient indoor environments in today’s workplace. This resulted from the fact that current guidelines are derived from empirical values and neglect the prevalence of computer-based tasks in current offices. A personal visual comfort model was designed to predict the degree of an individual’s visual comfort, as a way of evaluating the indoor lighting of the environment. Development of the model relied on experimental data, including individual eye pupil sizes, visual sensations, and visual satisfaction in response to various illuminance levels used for testsmore »of six human subjects. The results showed that (1) A personal comfort model was needed, (2) the personal comfort model produced a median accuracy of 0.7086 for visual sensation and 0.65467 for visual satisfaction for all subjects; (3) To develop a prediction model for the sample group, the Support Vector Machine algorithm,, outperformed the Logistic Regression and the Gaussian Naïve Bayes in terms of prediction accuracy. It was concluded that, a personal visual comfort model can use a building’s occupant’s eye pupil size to generate an accurate prediction of that occupant’s visual sensations and visual satisfaction that can, therefore, be applied with lighting control to improve the indoor environment and energy use in that building.« less