Biblio

Phishing has become a prominent method of data theft among hackers, and it continues to develop. In recent years, many strategies have been developed to identify phishing website attempts using machine learning particularly. However, the algorithms and classification criteria that have been used are highly different from the real issues and need to be compared. This paper provides a detailed comparison and evaluation of the performance of several machine learning algorithms across multiple datasets. Two phishing website datasets were used for the experiments: the Phishing Websites Dataset from UCI (2016) and the Phishing Websites Dataset from Mendeley (2018). Because these datasets include different types of class labels, the comparison algorithms can be applied in a variety of situations. The tests showed that Random Forest was better than other classification methods, with an accuracy of 88.92% for the UCI dataset and 97.50% for the Mendeley dataset.

Cyber threats have been a major issue in the cyber security domain. Every hacker follows a series of cyber-attack stages known as cyber kill chain stages. Each stage has its norms and limitations to be deployed. For a decade, researchers have focused on detecting these attacks. Merely watcher tools are not optimal solutions anymore. Everything is becoming autonomous in the computer science field. This leads to the idea of an Autonomous Cyber Resilience Defense algorithm design in this work. Resilience has two aspects: Response and Recovery. Response requires some actions to be performed to mitigate attacks. Recovery is patching the flawed code or back door vulnerability. Both aspects were performed by human assistance in the cybersecurity defense field. This work aims to develop an algorithm based on Reinforcement Learning (RL) with a Convoluted Neural Network (CNN), far nearer to the human learning process for malware images. RL learns through a reward mechanism against every performed attack. Every action has some kind of output that can be classified into positive or negative rewards. To enhance its thinking process Markov Decision Process (MDP) will be mitigated with this RL approach. RL impact and induction measures for malware images were measured and performed to get optimal results. Based on the Malimg Image malware, dataset successful automation actions are received. The proposed work has shown 98% accuracy in the classification, detection, and autonomous resilience actions deployment.

Machine learning (ML) models are increasingly being used in the development of Malware Detection Systems. Existing research in this area primarily focuses on developing new architectures and feature representation techniques to improve the accuracy of the model. However, recent studies have shown that existing state-of-the art techniques are vulnerable to adversarial machine learning (AML) attacks. Among those, data poisoning attacks have been identified as a top concern for ML practitioners. A recent study on clean-label poisoning attacks in which an adversary intentionally crafts training samples in order for the model to learn a backdoor watermark was shown to degrade the performance of state-of-the-art classifiers. Defenses against such poisoning attacks have been largely under-explored. We investigate a recently proposed clean-label poisoning attack and leverage an ensemble-based Nested Training technique to remove most of the poisoned samples from a poisoned training dataset. Our technique leverages the relatively large sensitivity of poisoned samples to feature noise that disproportionately affects the accuracy of a backdoored model. In particular, we show that for two state-of-the art architectures trained on the EMBER dataset affected by the clean-label attack, the Nested Training approach improves the accuracy of backdoor malware samples from 3.42% to 93.2%. We also show that samples produced by the clean-label attack often successfully evade malware classification even when the classifier is not poisoned during training. However, even in such scenarios, our Nested Training technique can mitigate the effect of such clean-label-based evasion attacks by recovering the model's accuracy of malware detection from 3.57% to 93.2%.

Cyberattack on power system brings new challenges on the development of modern power system. Hackers may implement false data injection attack (FDIA) to cause unstable operating conditions of the power system. However, data from different power internet of things usually contains a lot of redundancy, making it difficult for current efficient discriminant model to precisely identify FDIA. To address this problem, we propose a deep learning network-based data fusion model to handle features from measurement data in power system. Proposed model includes a data enrichment module and a data fusion module. We firstly employ feature engineering technique to enrich features from power system operation in time dimension. Subsequently, a long short-term memory based autoencoder (LSTM-AE) is designed to efficiently avoid feature space explosion problem during data enriching process. Extensive experiments are performed on several classical attack detection models over the load data set from IEEE 14-bus system and simulation results demonstrate that fused data from proposed model shows higher detection accuracy with respect to the raw data.

Phishing activity is undertaken by the hackers to compromise the computer networks and financial system. A compromised computer system or network provides data and or processing resources to the world of cybercrime. Cybercrimes are projected to cost the world \$6 trillion by 2021, in this context phishing is expected to continue being a growing challenge. Statistics around phishing growth over the last decade support this theory as phishing numbers enjoy almost an exponential growth over the period. Recent reports on the complexity of the phishing show that the fight against phishing URL as a means of building more resilient cyberspace is an evolving challenge. Compounding the problem is the lack of cyber security expertise to handle the expected rise in incidents. Previous research have proposed different methods including neural network, data mining technique, heuristic-based phishing detection technique, machine learning to detect phishing websites. However, recently phishers have started to use more sophisticated techniques to attack the internet users such as VoIP phishing, spear phishing etc. For these modern methods, the traditional ways of phishing detection provide low accuracy. Hence, the requirement arises for the application and development of modern tools and techniques to use as a countermeasure against such phishing attacks. Keeping in view the nature of recent phishing attacks, it is imperative to develop a state-of-the art anti-phishing tool which should be able to predict the phishing attacks before the occurrence of actual phishing incidents. We have designed such a tool that will work efficiently to detect the phishing websites so that a user can understand easily the risk of using of his personal and financial data.

Physical layer security is an emerging security area to tackle wireless security communications issues and complement conventional encryption-based techniques. Thus, we propose a novel scheme based on swarm intelligence optimization technique and a deep neural network (DNN) for maximizing the secrecy energy efficiency (SEE) in a cooperative relaying underlay cognitive radio- and non-orthogonal multiple access (NOMA) system with a non-linear energy harvesting user which is exposed to multiple eavesdroppers. Satisfactorily, simulation results show that the proposed particle swarm optimization (PSO)-DNN framework achieves close performance to that of the optimal solutions, with a meaningful reduction in computation complexity.

Recent advances in deep learning typically, with the introduction of transformer based models has shown massive improvement and success in many Natural Language Processing (NLP) tasks. One such area which has leveraged immensely is conversational agents or chatbots in open-ended (chit-chat conversations) and task-specific (such as medical or legal dialogue bots etc.) domains. However, in the era of automation, there is still a dearth of works focused on one of the most relevant use cases, i.e., tutoring dialog systems that can help students learn new subjects or topics of their interest. Most of the previous works in this domain are either rule based systems which require a lot of manual efforts or are based on multiple choice type factual questions. In this paper, we propose EDICA (Educational Domain Infused Conversational Agent), a language tutoring Virtual Agent (VA). EDICA employs two mechanisms in order to converse fluently with a student/user over a question and assist them to learn a language: (i) Student/Tutor Intent Classification (SIC-TIC) framework to identify the intent of the student and decide the action of the VA, respectively, in the on-going conversation and (ii) Tutor Response Generation (TRG) framework to generate domain infused and intent/action conditioned tutor responses at every step of the conversation. The VA is able to provide hints, ask questions and correct student's reply by generating an appropriate, informative and relevant tutor response. We establish the superiority of our proposed approach on various evaluation metrics over other baselines and state of the art models.

The smooth operation of metering equipment is inseparable from the monitoring and analysis of equipment alarm events by automated metering systems. With the generation of big data in power metering and the increasing demand for information security of metering systems in the power industry, how to use big data and protect data security at the same time has become a hot research field. In this paper, we propose a hybrid expert model based on federated learning to deal with the problem of alarm information analysis and identification. The hybrid expert system can divide the metering warning problem into multiple sub-problems for processing, which greatly improves the recognition and prediction accuracy. The experimental results show that our model has high accuracy in judging and identifying equipment faults.

Intrusion detection for Controller Area Network (CAN) protocol requires modern methods in order to compete with other electrical architectures. Fingerprint Intrusion Detection Systems (IDS) provide a promising new approach to solve this problem. By characterizing network traffic from known ECUs, hazardous messages can be discriminated. In this article, a modified version of Fingerprint IDS is employed utilizing both step response and spectral characterization of network traffic via neural network training. With the addition of feature set reduction and hyperparameter tuning, this method accomplishes a 99.4% detection rate of trusted ECU traffic.

Recently, internet services have increased rapidly due to the Covid-19 epidemic. As a result, cloud computing applications, which serve end-users as subscriptions, are rising. Cloud computing provides various possibilities like cost savings, time and access to online resources via the internet for end-users. But as the number of cloud users increases, so does the potential for attacks. The availability and efficiency of cloud computing resources may be affected by a Distributed Denial of Service (DDoS) attack that could disrupt services' availability and processing power. DDoS attacks pose a serious threat to the integrity and confidentiality of computer networks and systems that remain important assets in the world today. Since there is no effective way to detect DDoS attacks, it is a reliable weapon for cyber attackers. However, the existing methods have limitations, such as relatively low accuracy detection and high false rate performance. To tackle these issues, this paper proposes a Deep Generative Radial Neural Network (DGRNN) with a sigmoid activation function and Mutual Information Gain based Feature Selection (MIGFS) techniques for detecting DDoS attacks for the cloud environment. Specifically, the proposed first pre-processing step uses data preparation using the (Network Security Lab) NSL-KDD dataset. The MIGFS algorithm detects the most efficient relevant features for DDoS attacks from the pre-processed dataset. The features are calculated by trust evaluation for detecting the attack based on relative features. After that, the proposed DGRNN algorithm is utilized for classification to detect DDoS attacks. The sigmoid activation function is to find accurate results for prediction in the cloud environment. So thus, the proposed experiment provides effective classification accuracy, performance, and time complexity.

Emotion Detection through Facial feature recognition is an active domain of research in the field of human-computer interaction (HCI). Humans are able to share multiple emotions and feelings through their facial gestures and body language. In this project, in order to detect the live emotions from the human facial gesture, we will be using an algorithm that allows the computer to automatically detect the facial recognition of human emotions with the help of Convolution Neural Network (CNN) and OpenCV. Ultimately, Emotion Detection is an integration of obtained information from multiple patterns. If computers will be able to understand more of human emotions, then it will mutually reduce the gap between humans and computers. In this research paper, we will demonstrate an effective way to detect emotions like neutral, happy, sad, surprise, angry, fear, and disgust from the frontal facial expression of the human in front of the live webcam.

Artificial intelligence (AI) cooperates with multiple industries to improve the overall industry framework. Especially, human emotion recognition plays an indispensable role in supporting medical care, psychological counseling, crime prevention and detection, and crime investigation. The research on emotion recognition includes emotion-specific intonation patterns, literal expressions of emotions, and facial expressions. Recently, the deep learning model of facial emotion recognition aims to capture tiny changes in facial muscles to provide greater recognition accuracy. Hybrid models in facial expression recognition have been constantly proposed to improve the performance of deep learning models in these years. In this study, we proposed an ensemble learning algorithm for the accuracy of the facial emotion recognition model with three deep learning models: VGG16, InceptionResNetV2, and EfficientNetB0. To enhance the performance of these benchmark models, we applied transfer learning, fine-tuning, and data augmentation to implement the training and validation of the Facial Expression Recognition 2013 (FER-2013) Dataset. The developed algorithm finds the best-predicted value by prioritizing the InceptionResNetV2. The experimental results show that the proposed ensemble learning algorithm of priorities edges up 2.81% accuracy of the model identification. The future extension of this study ventures into the Internet of Things (IoT), medical care, and crime detection and prevention.

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explain aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.

The emergence of smart cars has revolutionized the automotive industry. Today's vehicles are equipped with different types of electronic control units (ECUs) that enable autonomous functionalities like self-driving, self-parking, lane keeping, and collision avoidance. The ECUs are connected to each other through an in-vehicle network, named Controller Area Network. In this talk, we will present the different cyber attacks that target autonomous vehicles and explain how an intrusion detection system (IDS) using machine learning can play a role in securing the Controller Area Network. We will also discuss the main research contributions for the security of autonomous vehicles. Specifically, we will describe our IDS, named Histogram-based Intrusion Detection and Filtering framework. Next, we will talk about the machine learning explainability issue that limits the acceptability of machine learning in autonomous vehicles, and how it can be addressed using our novel intrusion detection system based on rule extraction methods from Deep Neural Networks.

Keystroke dynamics is one solution to enhance the security of password authentication without adding any disruptive handling for users. Industries are looking for more security without impacting too much user experience. Considered as a friction-less solution, keystroke dynamics is a powerful solution to increase trust during user authentication without adding charge to the user. In this paper, we address the problem of user authentication considering the keystroke dynamics modality. We proposed a new approach based on the conversion of behavioral biometrics data (time series) into a 3D image. This transformation process keeps all the characteristics of the behavioral signal. The time series do not receive any filtering operation with this transformation and the method is bijective. This transformation allows us to train images based on convolutional neural networks. We evaluate the performance of the authentication system in terms of Equal Error Rate (EER) on a significant dataset and we show the efficiency of the proposed approach on a multi-instance system.

In this paper, we established a unified deep learning-based spam filtering method. The proposed method uses the message byte-histograms as a unified representation for all message types (text, images, or any other format). A deep convolutional neural network (CNN) is used to extract high-level features from this representation. A fully connected neural network is used to perform the classification using the extracted CNN features. We validate our method using several open-source text-based and image-based spam datasets.We obtained an accuracy higher than 94% on all datasets.

This work proposed a unified approach to increase the explainability of the predictions made by Convolution Neural Networks (CNNs) on medical images using currently available Explainable Artificial Intelligent (XAI) techniques. This method in-cooperates multiple techniques such as LISA aka Local Interpretable Model Agnostic Explanations (LIME), integrated gradients, Anchors and Shapley Additive Explanations (SHAP) which is Shapley values-based approach to provide explanations for the predictions provided by Blackbox models. This unified method increases the confidence in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists. In this work, a Chest X-ray (CXR) classification model for identifying Covid-19 patients is trained using transfer learning to illustrate the applicability of XAI techniques and the unified method (LISA) to explain model predictions. To derive predictions, an image-net based Inception V2 model is utilized as the transfer learning model.

With the rapid development of artificial intelligence (AI), many companies are moving towards automating their services using automated conversational agents. Dialogue-based conversational recommender agents, in particular, have gained much attention recently. The successful development of such systems in the case of natural language input is conditioned by the ability to understand the users’ utterances. Predicting the users’ intents allows the system to adjust its dialogue strategy and gradually upgrade its preference profile. Nevertheless, little work has investigated this problem so far. This paper proposes an LSTM-based Neural Network model and compares its performance to seven baseline Machine Learning (ML) classifiers. Experiments on a new publicly available dataset revealed The superiority of the LSTM model with 95% Accuracy and 94% F1-score on the full dataset despite the relatively small dataset size (9300 messages and 17 intents) and label imbalance.

Model compression is one of the most preferred techniques for efficiently deploying deep neural networks (DNNs) on resource- constrained Internet of Things (IoT) platforms. However, the simply compressed model is often vulnerable to adversarial attacks, leading to a conflict between robustness and efficiency, especially for IoT devices exposed to complex real-world scenarios. We, for the first time, address this problem by developing a novel framework dubbed Magical-Decomposition to simultaneously enhance both robustness and efficiency for hardware. By leveraging a hardware-friendly model compression method called singular value decomposition, the defending algorithm can be supported by most of the existing DNN hardware accelerators. To step further, by using a recently developed DNN interpretation tool, the underlying scheme of how the adversarial accuracy can be increased in the compressed model is highlighted clearly. Ablation studies and extensive experiments under various attacks/models/datasets consistently validate the effectiveness and scalability of the proposed framework.

Aiming at the prevention of information security risk in protection and control of smart substation, a multi-level security defense method of substation based on data aggregation and convolution neural network (CNN) is proposed. Firstly, the intelligent electronic device(IED) uses "digital certificate + digital signature" for the first level of identity authentication, and uses UKey identification code for the second level of physical identity authentication; Secondly, the device group of the monitoring layer judges whether the data report is tampered during transmission according to the registration stage and its own ID information, and the device group aggregates the data using the credential information; Finally, the convolution decomposition technology and depth separable technology are combined, and the time factor is introduced to control the degree of data fusion and the number of input channels of the network, so that the network model can learn the original data and fused data at the same time. Simulation results show that the proposed method can effectively save communication overhead, ensure the reliable transmission of messages under normal and abnormal operation, and effectively improve the security defense ability of smart substation.

The safety of the power system is inherently vital, due to the high risk of the electronic power system. In the wave of digitization in recent years, many power systems have been digitized to a certain extent. Under this circumstance, network security is particularly important, in order to ensure the normal operation of the power system. However, with the development of the Internet, network security issues are becoming more and more serious. Among all kinds of network attacks, the Distributed Denial of Service (DDoS) is a major threat. Once, attackers used huge volumes of traffic in short time to bring down the victim server. Now some attackers just use low volumes of traffic but for a long time to create trouble for attack detection. There are many methods for DDoS detection, but no one can fully detect it because of the huge volumes of traffic. In order to better detect DDoS and make sure the safety of electronic power system, we propose a novel detection method based on neural network. The proposed model and its service are deployed to the edge cloud, which can improve the real-time performance for detection. The experiment results show that our model can detect attacks well and has good real-time performance.

Most existing deep neural networks (DNNs) are inexplicable and fragile, which can be easily deceived by carefully designed adversarial example with tiny undetectable noise. This allows attackers to cause serious consequences in many DNN-assisted scenarios without human perception. In the field of speaker recognition, the attack for speaker recognition system has been relatively mature. Most works focus on white-box attacks that assume the information of the DNN is obtainable, and only a few works study gray-box attacks. In this paper, we study blackbox attacks on the speaker recognition system, which can be applied in the real world since we do not need to know the system information. By combining the idea of transferable attack and query attack, our proposed method NMI-FGSM-Tri can achieve the targeted goal by misleading the system to recognize any audio as a registered person. Specifically, our method combines the Nesterov accelerated gradient (NAG), the ensemble attack and the restart trigger to design an attack method that generates the adversarial audios with good performance to attack blackbox DNNs. The experimental results show that the effect of the proposed method is superior to the extant methods, and the attack success rate can reach as high as 94.8% even if only one query is allowed.

Tourism is one of the main sources of income in Australia. The number of tourists will affect airlines, hotels and other stakeholders. Predicting the arrival of tourists can make full preparations for welcoming tourists. This paper selects Queensland Tourism data as intelligent data. Carry out data visualization around the intelligent data, establish seasonal ARIMA model, find out the characteristics and predict. In order to improve the accuracy of prediction. Based on the tourism data around Queensland, build a 10 layer Back Propagation neural network model. It is proved that the network shows good performance for the data prediction of this paper.

Higher education management has problems producing 100% of graduates capable of responding to the needs of industry while industry also is struggling to find qualified graduates that responded to their needs in part because of the inefficient way of evaluating problems, as well as because of weaknesses in the evaluation of problem-solving capabilities. The objective of this paper is to propose an appropriate classification model to be used for predicting and evaluating the attributes of the data set of the student in order to meet the selection criteria required by the industries in the academic field. The dataset required for this analysis was obtained from a private firm and the execution was carried out using Chimp Optimization Algorithm (COA) based Deep Belief Neural Network (COA-DBNN) and the obtained results are compared with various classifiers such as Logistic Regression (LR), Decision Tree (DT) and Random Forest (RF). The proposed model outperforms other classifiers in terms of various performance metrics. This critical analysis will help the college management to make a better long-term plan for producing graduates who are skilled, knowledgeable and fulfill the industry needs as well.

Adversarial attacks have recently been proposed to scrutinize the security of deep neural networks. Most blackbox adversarial attacks, which have partial access to the target through queries, are target-specific; e.g., they require a well-trained surrogate that accurately mimics a given target. In contrast, target-agnostic black-box attacks are developed to attack any target; e.g., they learn a generalized surrogate that can adapt to any target via fine-tuning on samples queried from the target. Despite their success, current state-of-the-art target-agnostic attacks require tremendous fine-tuning steps and consequently an immense number of queries to the target to generate successful attacks. The high query complexity of these attacks makes them easily detectable and thus defendable. We propose a novel query-efficient target-agnostic attack that trains a generalized surrogate network to output the adversarial directions iv.r.t. the inputs and equip it with an effective fine-tuning strategy that only fine-tunes the surrogate when it fails to provide useful directions to generate the attacks. Particularly, we show that to effectively adapt to any target and generate successful attacks, it is sufficient to fine-tune the surrogate with informative samples that help the surrogate get out of the failure mode with additional information on the target’s local behavior. Extensive experiments on CIFAR10 and CIFAR-100 datasets demonstrate that the proposed target-agnostic approach can generate highly successful attacks for any target network with very few fine-tuning steps and thus significantly smaller number of queries (reduced by several order of magnitudes) compared to the state-of-the-art baselines.