This paper first describes the security and privacy challenges for the Internet of Things IoT) systems and then discusses some of the solutions that have been proposed. It also describes aspects of Trustworthy Machine Learning (TML) and then discusses how TML may be applied to handle some of the security and privacy challenges for IoT systems.

The computation of data trustworthiness during double-sided two-way-ranging with ultra-wideband signals between IoT devices is proposed. It relies on machine learning based ranging error correction, in which the certainty of the correction value is used to quantify trustworthiness. In particular, the trustworthiness score and error correction value are calculated from channel impulse response measurements, either using a modified k-nearest neighbor (KNN) or a modified random forest (RF) algorithm. The proposed scheme is easily implemented using commercial ultra-wideband transceivers and it enables real time surveillance of malicious or unintended modification of the propagation channel. The results on experimental data show an improvement of 47\% RMSE on the test set when only trustworthy measurements are considered.

Python continues to be one of the most popular programming languages and has been used in many safetycritical fields such as medical treatment, autonomous driving systems, and data science. These fields put forward higher security requirements to Python ecosystems. However, existing studies on machine learning systems in Python concentrate on data security, model security and model privacy, and just assume the underlying Python virtual machines (PVMs) are secure and trustworthy. Unfortunately, whether such an assumption really holds is still unknown.

We have seen the tremendous expansion of machine learning (ML) technology in Artificial Intelligence (AI) applications, including computer vision, voice recognition, and many others. The availability of a vast amount of data has spurred the rise of ML technologies, especially Deep Learning (DL). Traditional ML systems consolidate all data into a central location, usually a data center, which may breach privacy and confidentiality rules. The Federated Learning (FL) concept has recently emerged as a promising solution for mitigating data privacy, legality, scalability, and unwanted bandwidth loss problems. This paper outlines a vision for leveraging FL for better traffic steering predictions. Specifically, we propose a hierarchical FL framework that will dynamically update service function chains in a network by predicting future user demand and network state using the FL method.

In recent years, in order to continuously promote the construction of safe cities, security monitoring equipment has been widely used all over the country. How to use computer vision technology to realize effective intelligent analysis of violence in video surveillance is very important to maintain social stability and ensure people s life and property safety. Video surveillance system has been widely used because of its intuitive and convenient advantages. However, the existing video monitoring system has relatively single function, and generally only has the functions of monitoring video viewing, query and playback. In addition, relevant researchers pay less attention to the complex abnormal behavior of violence, and relevant research often ignores the differences between violent behaviors in different scenes. At present, there are two main problems in video abnormal behavior event detection: the video data of abnormal behavior is less and the definition of abnormal behavior in different scenes cannot be clearly distinguished. The main existing methods are to model normal behavior events first, and then define videos that do not conform to the normal model as abnormal, among which the learning method of video space-time feature representation based on deep learning shows a good prospect. In the face of massive surveillance videos, it is necessary to use deep learning to identify violent behaviors, so that the machine can learn to identify human actions, instead of manually monitoring camera images to complete the alarm of violent behaviors. Network training mainly uses video data set to identify network training.

Vulnerability Detection 2022 - With the booming development of deep learning and machine learning, the use of neural networks for software source code security vulnerability detection has become a hot pot in the field of software security. As a data structure, graphs can adequately represent the complex syntactic information, semantic information, and dependencies in software source code. In this paper, we propose the MPGVD model based on the idea of text classification in natural language processing. The model uses BERT for source code pre-training, transforms graphs into corresponding feature vectors, uses MPNN (Message Passing Neural Networks) based on graph neural networks in the feature extraction phase, and finally outputs the detection results. Our proposed MPGVD, compared with other existing vulnerability detection models on the same dataset CodeXGLUE, obtain the highest detection accuracy of 64.34\%.

Quantum Computing Security 2022 - As the development of quantum computing hardware is on the rise, its potential application to various research areas has been investigated, including to machine learning. Recently, there have been several initiatives to expand the work to quantum federated learning (QFL). However, challenges arise due to the fact that quantum computation poses different characteristics from classical computation, giving an even more challenge for a federated setting. In this paper, we present a highlevel overview of the current state of research in QFL. Furthermore, we also describe in brief about quantum computation and discuss its present limitations in relation to QFL development. Additionally, possible approaches to deploy QFL are explored. Lastly, remarks and challenges of QFL are also presented.

Privacy Policies - Privacy policies, despite the important information they provide about the collection and use of one’s data, tend to be skipped over by most Internet users. In this paper, we seek to make privacy policies more accessible by automatically classifying text samples into web privacy categories. We use natural language processing techniques and multiple machine learning models to determine the effectiveness of each method in the classification method. We also explore the effectiveness of these methods to classify privacy policies of Internet of Things (IoT) devices.

Predictive Security Metrics - With the emergence of Zero Trust (ZT) Architecture, industry leaders have been drawn to the technology because of its potential to handle a high level of security threats. The Zero Trust Architecture (ZTA) is paving the path for a security industrial revolution by eliminating location-based implicant access and focusing on asset, user, and resource security. Software Defined Perimeter (SDP) is a secure overlay network technology that can be used to implement a Zero Trust framework. SDP is a next-generation network technology that allows network architecture to be hidden from the outside world. It also hides the overlay communication from the underlay network by employing encrypted communications. With encrypted information, detecting abnormal behavior of entities on an overlay network becomes exceedingly difficult. Therefore, an automated system is required. We proposed a method in this paper for understanding the normal behavior of deployed polices by mapping network usage behavior to the policy. An Apache Spark collects and processes the streaming overlay monitoring data generated by the built-in fabric API in order to do this mapping. It sends extracted metrics to Prometheus for storage, and then uses the data for machine learning training and prediction. The cluster-id of the link that it belongs to is predicted by the model, and the cluster-ids are mapped onto the policies. To validate the legitimacy of policy, the labeled polices hash is compared to the actual polices hash that is obtained from blockchain. Unverified policies are notified to the SDP controller for additional action, such as defining new policy behavior or marking uncertain policies.

Predictive Security Metrics - Across the globe, renewable generation integration has been increasing in the last decades to meet ever-increasing power demand and emission targets. Wind power has dominated among various renewable sources due to the widespread availability and advanced low-cost technologies. However, the stochastic nature of wind power results in power system reliability and security issues. This is because the uncertain variability of wind power results in challenges to various system operations such as unit commitment and economic dispatch. Such problems can be addressed by accurate wind power forecasts to great extent. This attracted wider investigations for obtaining accurate power forecasts using various forecasting models such as time series, machine learning, probabilistic, and hybrid. These models use different types of inputs and obtain forecasts in different time horizons, and have different applications. Also, different investigations represent forecasting performance using different performance metrics. Limited classification reviews are available for these areas and detailed classification on these areas will help researchers and system operators to develop new accurate forecasting models. Therefore, this paper proposes a detailed review of those areas. It concludes that even though quantum investigations are available, wind power forecasting accuracy improvement is an ever-existing research problem. Also, forecasting performance indication in financial term such as deviation charges can be used to represent the economic impact of forecasting accuracy improvement.

Predictive Security Metrics - This paper belongs to a sequence of manuscripts that discuss generic and easy-to-apply security metrics for Strong PUFs. These metrics cannot and shall not fully replace in-depth machine learning (ML) studies in the security assessment of Strong PUF candidates. But they can complement the latter, serve in initial PUF complexity analyses, and are much easier and more efficient to apply: They do not require detailed knowledge of various ML methods, substantial computation times, or the availability of an internal parametric model of the studied PUF. Our metrics also can be standardized particularly easily. This avoids the sometimes inconclusive or contradictory findings of existing ML-based security test, which may result from the usage of different or non-optimized ML algorithms and hyperparameters, differing hardware resources, or varying numbers of challenge-response pairs in the training phase.

Object Oriented Security - Aerial surveillance plays an important role for security applications. It can be further used to monitor borders, restricted zones and critical infrastructure. With the help of drones one can perform surveillance and get the exact location of various objects. Aerial object detection comes with many challenges like the object size which can be as low as 20×20 pixels. Images taken from satellites are hundreds of megapixels. Traditional methods like Histogram of oriented gradients (HOG) and Scale invariant feature transformation (SIFT) were used to extract features from the objects. Then these features were given to machine learning classifier like logistic regression, Support vector machine (SVM) and Random forest (RF) for detection and classification. However, the issue with these methods is that they are highly inaccurate and generated many false detections and misclassifications too. With the evolution of Graphics processing units (GPU) and the introduction of convolutional neural networks (CNN) as well as Deep Learning algorithms situation got changed. Now, it is possible to extract more information and provide better accuracy. In this paper for object detection You only look once version 4 (YOLOv4) is used which is one of the state-of-the-art algorithms. It uses Darknet 53 which is a type of CNN as a backbone for feature extraction. In this work the YOLOv4 based proposed system detect and localize vehicles present in the restricted zone and then geotag them.

Neural Style Transfer - Image style transfer is an important research content related to image processing in computer vision. Compared with traditional artificial computing methods, deep learning-based convolutional neural networks in the field of machine learning have powerful advantages. This new method has high computational efficiency and a good style transfer effect. To further improve the quality and efficiency of image style transfer, the pre-trained VGG-16 neural network model and VGG-19 neural network model are used to achieve image style transfer, and the transferred images generated by the two neural networks are compared. The research results show that the use of the VGG-16 convolutional neural network to achieve image style transfer is better and more efficient.

Neural Network Security - Software-Defined Network (SDN) is a new networking paradigm that adopts centralized control logic and provides more control to the network operators over the network infrastructure to meet future network requirements. SDN controller known as operation system, which is responsible for running network applications and maintaining the different network services and functionalities. Despite all its great capabilities, SDN is facing different security threats due to its various architectural entities and centralized nature. Distributed Denial of Service (DDoS) is a promptly growing attack and becomes a major threat for the SDN. To date, most of the studies focus on detecting high-rate DDoS attacks at the control layer of SDN and low-rate DDoS attacks are high concealed because they are difficult to detect. Furthermore, the existing methods are useful for the detection of high-rate DDoS, so need to focus on low-rate DDoS attacks separately. Hence, the use of machine learning algorithms is growing for the detection of low-rate DDoS attacks in the SDN, but they achieved low accuracy against this attack. To improve the detection accuracy, this paper first describes the attack s mechanism and then proposes a Recurrent Neural Network (RNN) based method. The extracted features from the flow rules are used by the RNN for the detection of low-rate attacks. The experimental results show that the proposed method intelligently detects the attack, and its detection accuracy reaches 98.59\%. The proposed method achieves good detection accuracy as compared to existing studies.

Neural Network Security - Aiming at the network security problem caused by the rapid development of network, this paper uses a network traffic anomaly detection method of industrial control system based on convolutional neural network. In the traditional machine learning algorithm, the processing of features has a high impact on the performance of the model, and the model is highly dependent on features. This method uses the characteristics of convolutional neural network to autonomously learn features, which avoids this problem. In order to verify the superiority of the model, this paper takes accuracy as the evaluation index, and compares it with the traditional machine learning algorithm. The results show that the overall accuracy of the method is 99.88 \%, which has higher accuracy than traditional machine learning algorithms such as decision tree algorithm (ID3), adaptive boosting tree (Adboost) and naive Bayesian model. Therefore, this method can be better applied to the anomaly detection of network traffic in industrial control system, and has practical application value.

Neural Network Security - With the development of computing technology, data security and privacy protection have also become the focus of researchers; along with this comes the issue of network link security and reliability, and these issues have become the focus of discussion when studying network security. Intrusion detection is an effective means to assist in network malicious traffic detection and maintain network stability; to meet the ever-changing demand for network traffic identification, intrusion detection models have undergone a transformation from traditional intrusion detection models to machine learning intrusion detection models to deep intrusion detection models. The efficiency and superiority of deep learning have been proven in fields such as image processing, but there are still some problems in the field of network security intrusion detection: the models are not targeted when processing data, the models have poor generalization ability, etc. The combinatorial neural network proposed in this paper can effectively propose a solution to the problems of existing models, and the CL-IDS model proposed in this paper has a better performance on the KDDCUP99 dataset as demonstrated by relevant experiments.

Neural Network Resiliency - With the proliferation of Low Earth Orbit (LEO) spacecraft constellations, comes the rise of space-based wireless cognitive communications systems (CCS) and the need to safeguard and protect data against potential hostiles to maintain widespread communications for enabling science, military and commercial services. For example, known adversaries are using advanced persistent threats (APT) or highly progressive intrusion mechanisms to target high priority wireless space communication systems. Specialized threats continue to evolve with the advent of machine learning and artificial intelligence, where computer systems inherently can identify system vulnerabilities expeditiously over naive human threat actors due to increased processing resources and unbiased pattern recognition. This paper presents a disruptive abuse case for an APT-attack on such a CCS and describes a trade-off analysis that was performed to evaluate a variety of machine learning techniques that could aid in the rapid detection and mitigation of an APT-attack. The trade results indicate that with the employment of neural networks, the CCS s resiliency would increase its operational functionality, and therefore, on-demand communication services reliability would increase. Further, modelling, simulation, and analysis (MS\&A) was achieved using the Knowledge Discovery and Data Mining (KDD) Cup 1999 data set as a means to validate a subset of the trade study results against Training Time and Number of Parameters selection criteria. Training and cross-validation learning curves were computed to model the learning performance over time to yield a reasonable conclusion about the application of neural networks.

Network Security Resiliency - Distributed cyber-infrastructures and Artificial Intelligence (AI) are transformative technologies that will play a pivotal role in the future of society and the scientific community. Internet of Things (IoT) applications harbor vast quantities of connected devices that collect a massive amount of sensitive information (e.g., medical, financial), which is usually analyzed either at the edge or federated cloud systems via AI/Machine Learning (ML) algorithms to make critical decisions (e.g., diagnosis). It is of paramount importance to ensure the security, privacy, and trustworthiness of data collection, analysis, and decision-making processes. However, system complexity and increased attack surfaces make these applications vulnerable to system breaches, single-point of failures, and various cyber-attacks. Moreover, the advances in quantum computing exacerbate the security and privacy challenges. That is, emerging quantum computers can break conventional cryptographic systems that offer cyber-security services, public key infrastructures, and privacy-enhancing technologies. Therefore, there is a vital need for new cyber-security paradigms that can address the resiliency, long-term security, and efficiency requirements of distributed cyber infrastructures.

Network Intrusion Detection - With the development of computing technology, data security and privacy protection have also become the focus of researchers; along with this comes the issue of network link security and reliability, and these issues have become the focus of discussion when studying network security. Intrusion detection is an effective means to assist in network malicious traffic detection and maintain network stability; to meet the ever-changing demand for network traffic identification, intrusion detection models have undergone a transformation from traditional intrusion detection models to machine learning intrusion detection models to deep intrusion detection models. The efficiency and superiority of deep learning have been proven in fields such as image processing, but there are still some problems in the field of network security intrusion detection: the models are not targeted when processing data, the models have poor generalization ability, etc. The combinatorial neural network proposed in this paper can effectively propose a solution to the problems of existing models, and the CL-IDS model proposed in this paper has a better performance on the KDDCUP99 dataset as demonstrated by relevant experiments.

Nearest Neighbor Search - One of the most significant and widely used IT breakthroughs nowadays is cloud computing. Today, the majority of enterprises use private or public cloud computing services for their computing infrastructure. Cyber-attackers regularly target Cloud resources by inserting malicious code or obfuscated malware onto the server. These malware programmes that are obfuscated are so clever that they often manage to evade the detection technology that is in place. Unfortunately, they are discovered long after they have done significant harm to the server. Machine Learning (ML) techniques have shown to be effective at finding malware in a wide range of fields. To address feature selection (FS) challenges, this study uses the wrapperbased Binary Bat Algorithm (BBA), Cuckoo Search Algorithm (CSA), Mayfly Algorithm (MA), and Particle Swarm Optimization (PSO), and then k-Nearest Neighbor (kNN), Random Forest (RF), and Support Vector Machine (SVM) are used to classify the benign and malicious records to measure the performance in terms of various metrics. CIC-MalMem-2022, the most recent malware memory dataset, is used to evaluate and test the proposed approach and it is found that the proposed system is an acceptable solution to detect malware.

Nearest Neighbor Search - Network security is one of the main challenges faced by network administrators and owners, especially with the increasing numbers and types of attacks. This rapid increase results in a need to develop different protection techniques and methods. Network Intrusion Detection Systems (NIDS) are a method to detect and analyze network traffic to identify attacks and notify network administrators. Recently, machine learning (ML) techniques have been extensively applied in developing detection systems. Due to the high complexity of data exchanged over the networks, applying ML techniques will negatively impact system performance as many features need to be analyzed. To select the most relevant features subset from the input data, a feature selection technique is used, which results in enhancing the overall performance of the NIDS. In this paper, we propose a wrapper approach as a feature selection based on a Chaotic Crow Search Algorithm (CCSA) for anomaly network intrusion detection systems. Experiments were conducted on the LITNET2020 dataset. To the best of our knowledge, our proposed method can be considered the first selection algorithm applied on this dataset based on swarm intelligence optimization to find a special subset of features for binary and multiclass classifications that optimizes the performance for all classes at the same time.The model was evaluated using several ML classifiers namely, Knearest neighbors (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Multi-layer perceptron (MLP), and Long Short-Term Memory (LSTM). The results proved that the proposed algorithm is more efficient in improving the performance of NIDS in terms of accuracy, detection rate, precision, F-score, specificity, and false alarm rate, outperforming state-of-the-art feature selection techniques recently proposed in the literature.

Natural Language Processing - Dissemination of fake news is a matter of major concern that can result in national and social damage with devastating impacts. The misleading information on the internet is dubious and seems to be arduous for identification. Machine learning models are becoming an irreplaceable component in the detection of fake news spreading on the social media. LSTM is a memory based machine learning model for the detection of false news. LSTM has a promising approach and eradicates the issue of vanishing gradient in RNNs. The integration of natural language processing and LSTM model is considered to be effective in the false news identification.

Natural Language Processing - In today’s digital era, online attacks are increasing in number and are becoming severe day by day, especially those related to web applications. The data accessible over the web persuades the attackers to dispatch new kinds of attacks. Serious exploration on web security has shown that the most hazardous attack that affects web security is the Structured Query Language Injection(SQLI). This attack addresses a genuine threat to web application security and a few examination works have been directed to defend against this attack by detecting it when it happens. Traditional methods like input validation and filtering, use of parameterized queries, etc. are not sufficient to counter these attacks as they rely solely on the implementation of the code hence factoring in the developer’s skill-set which in turn gave rise to Machine Learning based solutions. In this study, we have proposed a novel approach that takes the help of Natural Language Processing(NLP) and uses BERT for feature extraction that is capable to adapt to SQLI variants and provides an accuracy of 97\% with a false positive rate of 0.8\% and a false negative rate of 5.8\%.

Natural Language Processing - This paper presents a system to identify social engineering attacks using only text as input. This system can be used in different environments which the input is text such as SMS, chats, emails, etc. The system uses Natural Language Processing to extract features from the dialog text such as URL s report and count, spell check, blacklist count, and others. The features are used to train Machine Learning algorithms (Neural Network, Random Forest and SVM) to perform classification of social engineering attacks. The classification algorithms showed an accuracy over 80\% to detect this type of attacks.

Named Data Network Security - With the growing recognition that current Internet protocols have significant security flaws; several ongoing research projects are attempting to design potential next-generation Internet architectures to eliminate flaws made in the past. These projects are attempting to address privacy and security as their essential parameters. NDN (Named Data Networking) is a new networking paradigm that is being investigated as a potential alternative for the present host-centric IP-based Internet architecture. It concentrates on content delivery, which is probably underserved by IP, and it prioritizes security and privacy. NDN must be resistant to present and upcoming threats in order to become a feasible Internet framework. DDoS (Distributed Denial of Service) attacks are serious attacks that have the potential to interrupt servers, systems, or application layers. Due to the probability of this attack, the network security environment is made susceptible. The resilience of any new architecture against the DDoS attacks which afflict today s Internet is a critical concern that demands comprehensive consideration. As a result, research on feature selection approaches was conducted in order to use machine learning techniques to identify DDoS attacks in NDN. In this research, features were chosen using the Information Gain and Data Reduction approach with the aid of the WEKA machine learning tool to identify DDoS attacks. The dataset was tested using KNearest Neighbor (KNN), Decision Table, and Artificial Neural Network (ANN) algorithms to categorize the selected features. Experimental results shows that Decision Table classifier outperforms well when compared to other classification algorithms with the with the accuracy of 85.42\% and obtained highest precision and recall score with 0.876 and 0.854 respectively when compared to the other classification techniques.