Intrusion Detection of Imbalanced Network Traffic Based on

Machine Learning and Deep Learning

ABSTRACT: In imbalanced network traffic, malicious cyber-attacks can
often hide in large amounts of normal data. It exhibits a high degree of stealth
and obfuscation in cyberspace, making it difficult for Network Intrusion
Detection System (NIDS) to ensure the accuracy and timeliness of detection.
This paper researches machine learning and deep learning for intrusion
detection in imbalanced network traffic. It proposes a novel Difficult Set
Sampling Technique (DSSTE) algorithm to tackle the class imbalance problem.
First, use the Edited Nearest Neighbor (ENN) algorithm to divide the
imbalanced training set into the difficult set and the easy set. Next, use the
KMeans algorithm to compress the majority samples in the difficult set to
reduce the majority. Zoom in and out the minority samples continuous attributes
in the difficult set synthesize new samples to increase the minority number.
Finally, the easy set, the compressed set of majority in the difficult, and the
minority in the difficult set are combined with its augmentation samples to
make up a new training set. The algorithm reduces the imbalance of the original
training set and provides targeted data augment for the minority class that needs
to learn. It enables the classifier to learn the differences in the training stage
better and improve classification performance. To verify the proposed method,
we conduct experiments on the classic intrusion dataset NSL-KDD and the
newer and comprehensive intrusion dataset CSE-CIC-IDS2018. We use
classical classification models: random forest(RF), Support Vector
Machine(SVM), XGBoost, Long and Short-term Memory(LSTM), AlexNet,
Mini-VGGNet. We compare the other 24 methods; the experimental results
demonstrate that our proposed DSSTE algorithm outperforms the other
methods.
Robust and Efficient Classification for Underground Metal
Target Using Dimensionality Reduction and Machine Learning
ABSTRACT: Underground metal target detection technology has been
widely applied in industrial production, resource exploration, and engineering
construction, etc. However, due to the influence of nonnegligible noise and high
dimensionality in collected data, achieving efficient and accurate underground
target classification remains a grand challenge for further applications of
underground metal target detection on portable devices with limited computing
capability and energy supply. This study aimed to seek out robust and efficient
data-based strategies to classify the underground metal targets of different
shapes and materials based on electromagnetic induction detection. We
investigated thirty-three classification strategies based on eleven dimensionality
reduction methods, namely, the least absolute shrinkage and selection operator
(LASSO), genetic algorithm-support vector machine (GA-SVM), Pearson
correlation coefficient (PCC), mutual information (MI), maximal relevance
minimal redundancy Pearson correlation (mRMRP), maximal relevance
minimal redundancy mutual information (mRMRMI), statistical features (SF),
principal component analysis (PCA), kernel principal component analysis
(KPCA), locally linear embedding (LLE), and stacked denoising autoencoder
(SDAE), and three machine learning models, namely, artificial neural network
(ANN), linear support vector machine (L-SVM), and Gaussian Naïve Bayes
(GNB). Several parameters, including classification accuracy, the number of
features after dimensionality, the feature type importance, and the time
consumption were considered to evaluate the data-based classification
strategies. Among the classification strategies investigated and considering the
above evaluation parameters, the artificial neural network (ANN) classifier
assisted with the kernel principal component analysis (KPCA) feature extraction
method yielded the best performance in the material-based classification
(accuracy:0.99) and the shape-based classification (accuracy:0.99). The locally
linear embedding (LLE) improved the robustness of machine learning
classifiers and efficiency of the artificial neural network in the material-based
classification (improvement of average accuracy:0.17, reduction of
classification time cost:14%) and shapebased classification (improvement of
average accuracy:0.16, reduction of classification time cost:22%). Our
comparative investigation provides a robust and efficient data-based strategy for
underground metal target classification, which is significant for applications of
underground metal target detection on portable devices with limited computing
capability and energy supply. The cross-combination strategy of dimensionality
reduction methods and machine learning models provides a way to find the
optimal machine learning model for underground target detection.
Action-Decision Networks for Visual Tracking with Deep
Reinforcement Learning
ABSTRACT: This paper proposes a novel tracker which is controlled by
sequentially pursuing actions learned by deep reinforcement learning. In
contrast to the existing trackers using deep networks, the proposed tracker is
designed to achieve a light computation as well as satisfactory tracking
accuracy in both location and scale. The deep network to control actions is pre-
trained using various training sequences and fine-tuned during tracking for
online adaptation to target and background changes. The pre-training is done by
utilizing deep reinforcement learning as well as supervised learning. The use of
reinforcement learning enables even partially labeled data to be successfully
utilized for semi-supervised learning. Through evaluation of the OTB dataset,
the proposed tracker is validated to achieve a competitive performance that is
three times faster than stateof-the-art, deep network–based trackers. The fast
version of the proposed method, which operates in real-time on GPU,
outperforms the state-of-the-art real-time trackers.

A Deep Learning-based Fine-grained Hierarchical

Learning Approach for Robust Malware Classification
ABSTRACT: The wide acceptance of Internet of Things (IoT) for both
household and industrial applications is accompanied by several security
concerns. A major security concern is their probable abuse by adversaries
towards their malicious intent. Understanding and analyzing IoT malicious
behaviors is crucial, especially with their rapid growth and adoption in wide-
range of applications. Among the variety of employed techniques, static and
dynamic analyses are the most common approaches to detect and classify
malware. Given the limited scalability of dynamic analysis, static analysis, such
as the use of Control Flow Graph (CFG)-based features, is widely used by
machine learning algorithms for malware analysis and detection. However,
recent studies have shown that machine learning-based approaches are
susceptible to adversarial attacks by adding junk codes to the binaries, for
example, with an intention to fool those machine learning or deep learning-
based detection systems. Realizing the importance of addressing this challenge,
this study proposes a malware detection system that is robust to adversarial
attacks. To do so, examine the performance of the state-of-the-art methods
against adversarial IoT software crafted using the graph embedding and
augmentation techniques. In particular, we study the robustness of such methods
against two black-box adversarial methods, GEA and SGEA, to generate
Adversarial Examples (AEs) with reduced overhead, and keeping their
practicality intact. Our comprehensive experimentation with GEA-based AEs
show the relation between misclassification and the graph size of the injected
sample. Upon optimization and with small perturbation, by use of SGEA, all the
IoT malware samples are misclassified as benign. This highlights the
vulnerability of current detection systems under adversarial settings. With the
landscape of possible adversarial attacks, we then propose DL-FHMC, a fine-
grained hierarchical learning approach for malware detection and classification,
that is robust to AEs with a capability to detect 88.52% of the malicious AEs.
Detecting Twitter Cyberbullying Using Machine Learning
ABSTRACT: Online media is a stage where numerous youthful individuals
are getting tormented. As person to person communication destinations are
expanding, cyberbullying is expanding step by step. To recognize word
likenesses in the tweets made by menaces and utilize AI and can build up a ML
model naturally recognize online media tormenting activities. In any case,
numerous online media tommenting identification methods have been
actualized, however numerous of them were printed based. The objective of this
paper is to show the execution of programming that will distinguish tormented
tweets, posts, and so on An AI model is proposed to distinguish and forestall
tormenting on Twitter. Two classifiers for example SVM and RF are utilized for
preparing and testing the online media tormenting content. Both SVM (Support
Vector Machine) and RF had the option to recognize the genuine positives with
71.25% and 52.70% precision individually. Yet, SVM beats RF of comparable
work on the equivalent dataset
COMPARISON OF MACHINE LEARNING ALGORITHMS
FOR PREDICTING CRIME HOTSPORTS
ABSTRACT: Crime prediction is of great significance to the formulation of
policing strategies and the implementation of crime prevention and control.
Machine learning is the current mainstream prediction method. However, few
studies have systematically compared different machine learning methods for
crime prediction. This paper takes the historical data of public property crime
from 2015 to 2018 from a section of a large coastal city in the southeast of
China as research data to assess the predictive power between several machine
learning algorithms. Results based on the historical crime data alone suggest
that the LSTM model outperformed KNN, random forest, support vector
machine, naive Bayes, and convolutional neural networks. In addition, the built
environment data of points of interests (POIs) and urban road network density
are input into LSTM model as covariates. It is found that the model with built
environment covariates has better prediction effect compared with the original
model that is based on historical crime data alone. Therefore, future crime
prediction should take advantage of both historical crime data and covariates
associated with criminological theories. Not all machine learning algorithms are
equally effective in crime prediction.