Different Types Of Attacks Research Articles

Defending against Backdoor Attacks in Natural Language Generation

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has been invested to how backdoor attacks can affect current NLG models and how to defend against these attacks. In this work, by giving a formal definition of backdoor attack and defense, we investigate this problem on two important NLG tasks, machine translation and dialog generation. Tailored to the inherent nature of NLG models (e.g., producing a sequence of coherent words given contexts), we design defending strategies against attacks. We find that testing the backward probability of generating sources given targets yields effective defense performance against all different types of attacks, and is able to handle the one-to-many issue in many NLG tasks such as dialog generation. We hope that this work can raise the awareness of backdoor risks concealed in deep NLG systems and inspire more future work (both attack and defense) towards this direction.

DDoS Attack Detection and Classification Using Hybrid Model for Multicontroller SDN

A software-defined network (SDN) brings a lot of advantages to the world of networking through flexibility and centralized management; however, this centralized control makes it susceptible to different types of attacks. Distributed denial of service (DDoS) is one of the most dangerous attacks that are frequently launched against the controller to put it out of service. This work takes the special ability of SDN to propose a solution that is an implementation run at the multicontroller to detect a DDoS attack at the early stage. This method not only detects the attacks but also identifies the attacking paths and starts a mitigation process to provide protection for the network devices. This method is based on the entropy variation of the destination host targeted with its IP address and can detect the attack within the first 250 packets of malicious traffic attacking a particular host. Then, fine-grained packet-based detection is performed using a deep-learning model to classify the attack into different types of attack categories. Lastly, the controller sends the updated traffic information to neighbor controllers. The chi-squared ( x 2 ) test feature selection algorithm was also employed to reveal the most relevant features that scored the highest in the provided data set. The experiment result demonstrated that the proposed Long Short-Term Memory (LSTM) model achieved an accuracy of up to 99.42% using the data set CICDDoS2019, which has the potential to detect and classify the DDoS attack traffic effectively in the multicontroller SDN environment. In this regard, it has an enhanced accuracy level to 0.42% compared with the RNN-AE model with data set CICDDoS2019, while it has improved up to 0.44% in comparison with the CNN model with the different data set ICICDDoS2017.

Digital Watermarking

The paper introduces the digital watermarking technology which is a data hiding technique that embeds a message into a multimedia work such as an image or text or other digital object. The proposed technique has several important applications; the majorly important is the digital copyrights protection. The digital watermarking system as any other data hiding technique has its own requirements that make the digital watermark strong as possible. Technologies of digital watermarking are mainly classified depending on their domain to spatial domain watermarks, Watermarks belonging to frequency (transform) domain and wavelet domain watermarks. The digital watermarks suffer from different types of attacks that include either state-of-the-art watermarking attacks or watermark estimation attacks. The recovery from these attacks requires strong detection techniques; the digital watermark agent provides a professional solution for these attacks.

Combined image encryption and steganography technique for enhanced security using multiple chaotic maps

This paper proposes a novel security algorithm which combines the concepts of Cryptography and Steganography to provide enhanced security to digital images. The proposed algorithm, named CIEST, enciphers the secret image (cryptography) which is hidden into the cover image (steganography) for secured transfer of information. A two-stage encryption process, with one of the stages being DNA encoding is used here. The cover image is also modified before the data embedding phase to improve the effectiveness of the algorithm. Multiple Combined Chaotic maps are utilised in the encryption and embedding stages to improve the randomness of the algorithm. The use of chaotic maps also makes the algorithm more robust to different types of attacks. The CIEST scheme is shown to be robust, offering high embedding capacity with high sensitivity with a near zero correlation value, information entropy value of 7.9972, maximum SSIM of 0.9992, and a maximum PSNR of 56.1071. The experimental results presented establish the immunity of the proposed method against attacks along with the feasibility and effectiveness of the algorithm in real time.

Enhancing intrusion detection in IoT systems: A hybrid metaheuristics-deep learning approach with ensemble of recurrent neural networks

Significant benefits have been brought to various industries by IoT (Internet of Things), but new security challenges have also been introduced due to the sheer volume and complexity of IoT systems. The protection of IoT systems from attacks and the assurance of their security posture are ensured by intrusion detection systems (IDSs). Recently, machine learning (ML) strategies have been broadly adopted for IDSs in IoT systems. However, there is still room for improvement, particularly in addressing the physical and functional diversity of IoT systems. A hybrid metaheuristics-deep learning approach is proposed in this paper for enhancing intrusion detection in IoT systems. An advanced metaheuristics algorithm with an ensemble of recurrent neural networks (RNNs) can be utilized to enhance the intrusion detection in IoT. Different types of attacks in IoT systems are identified by employing LSTM and GRU models, which constitute the RNNs. Feature selections are performed using Harris hawk optimization and fractional derivative mutation, as employed in this paper. To assess the proposed approach, publicly available datasets were utilized, and the empirical analysis demonstrated that the proposed approach works well than the other related methods in terms of accuracy and efficiency. Overall, the proposed work presents a promising solution for enhancing intrusion detection in IoT systems, and it has the potential to serve as a foundation for future research in this field.

Iliash Implementation of the password complexity diagnostic system

Password diagnostic systems are becoming increasingly relevant in the modern world due to the growth of internet services and the need to protect personal data. Evaluating password complexity allows for assessing the strength of passwords against different types of attacks, including brute force, dictionary attacks, and other methods. In this work, a system for checking password complexity was developed, which takes into account new approaches to forming the uniqueness of the selected sequence of characters. As opposed to standard methods used in the most common password generating systems, such as length, the presence of special characters and numbers, and the use of upper and lower case letters, this work proposes to check for repetitions and matches with the most common passwords. For this purpose, a database of 10,000 passwords was connected to the developed system. To speed up the checking for matches, the Levenshtein distance algorithm was used. The Levenshtein algorithm works using dynamic programming. It considers two strings that need to be compared and creates a matrix that shows the minimum number of editing operations required to transform one string into the other. This implementation allowed for faster password generation compared to existing systems. The work details the algorithms for all the main stages of password complexity checking and proposes code implementation in Javascript. The Levenshtein algorithm can be useful for determining text similarity or searching for possible correct variants of misspelled words. It can also be used for implementing autocomplete in programs that use user input. The implemented system can be integrated into many different programs and web services for automatic password complexity determination, allowing for its use in various areas such as banking, medical services, and others. As a result of work on this project, it has been confirmed that using a password complexity diagnostic system can significantly reduce the risk of unauthorized access to systems containing important confidential information.

Double image encryption based on a hybrid phase-truncation scheme

We propose a double image encryption approach based on a hybrid phase-truncation scheme. This approach is realized by spatial and Fresnel encoding, where two plaintexts are encrypted by a random amplitude mask into two private key masks and one ciphertext mask. The random amplitude mask is introduced to break the functional relation of the plaintexts to the ciphertext. Compared with other reported phase-truncation-based techniques, the proposed hybrid scheme is not only free from information leakage but also resistant to several different types of attacks. In addition, the parameters of the Fresnel transform and discrete multiple parameter fractional Fourier transform serve as additional keys to strengthen security significantly. Numerical simulations and a performance analysis are conducted to demonstrate the reliability and validity of the proposed approach.

Application Layer-Based Denial-of-Service Attacks Detection against IoT-CoAP

Internet of Things (IoT) is a massive network based on tiny devices connected internally and to the internet. Each connected device is uniquely identified in this network through a dedicated IP address and can share the information with other devices. In contrast to its alternatives, IoT consumes less power and resources; however, this makes its devices more vulnerable to different types of attacks as they cannot execute heavy security protocols. Moreover, traditionally used heavy protocols for web-based communication, such as the Hyper Text Transport Protocol (HTTP) are quite costly to be executed on IoT devices, and thus specially designed lightweight protocols, such as the Constrained Application Protocol (CoAP) are employed for this purpose. However, while the CoAP remains widely-used, it is also susceptible to attacks, such as the Distributed Denial-of-Service (DDoS) attack, which aims to overwhelm the resources of the target and make them unavailable to legitimate users. While protocols, such as the Datagram Transport Layer Security (DTLS) and Lightweight and the Secure Protocol for Wireless Sensor Network (LSPWSN) can help in securing CoAP against DDoS attacks, they also have their limitations. DTLS is not designed for constrained devices and is considered as a heavy protocol. LSPWSN, on the other hand, operates on the network layer, in contrast to CoAP which operates on the application layer. This paper presents a machine learning model, using the CIDAD dataset (created on 11 July 2022), that can detect the DDoS attacks against CoAP with an accuracy of 98%.

Secure authentication and data aggregation scheme for routing packets in wireless sensor network

<span lang="EN-US">Wireless sensor networks (WSNs) comprise a huge number of sensors that sense real-time data; in general, WSNs are designed for monitoring in various application mainly internet of things based (IoT) application. Moreover, these sensors possess a certain amount of energy i.e., they are battery based; thus, the network model must be efficient. Furthermore, data aggregation is a mechanism that minimizes the energy; however, in addition, these aggregated data and networks can be subject to different types of attacks due to the vulnerable characteristics of the network. Hence it is important to provide end-to-end security in the data aggregation mechanism in this we design and develop dual layer integrated (DLI)-security architecture for secure data aggregation; DLI-security architecture is an integration of two distinctive layers. The first layer of architecture deals with developing an authentication for reputation-based communication; the second layer of architecture focuses on securing the aggregated data through a consensus-based approach. The experiment outcome shows that DLI identifies the correct data packets and discards the unsecured data packets in energy efficient way with minimal computation overhead and higher throughput in comparison with the existing model.</span>

Control of Web Traffic Using Web Application Firewall : Techniques and Challenges

The increasing complexity and sophistication of web-based applications have made them vulnerable to various security threats. Web Application Firewalls (WAFs) have emerged as an essential security measure to protect web applications from common attacks such as SQL injection, cross-site scripting (XSS), and others. This research paper explores the techniques and challenges involved in controlling web traffic using a Web Application Firewall. The paper discusses the working principles of WAFs, the various methods employed to analyze and filter web traffic, and the effectiveness of these techniques in mitigating different types of attacks. Additionally, the paper highlights the challenges faced in deploying and managing WAFs and provides insights into potential future developments in the field. This research paper delves into the techniques and challenges associated with controlling web traffic using a Web Application Firewall. It explores the fundamental principles of WAFs, including signature-based filtering, behavior-based analysis, whitelisting, blacklisting, rate limiting, and protection against common vulnerabilities. The paper evaluates the effectiveness of these techniques in mitigating various attacks and highlights the challenges involved in deploying and managing WAFs, such as configuration complexity, false positives and negatives, performance impact, and integration with existing security infrastructure. Furthermore, the paper discusses emerging trends and potential future directions in the field, including the integration of machine learning and artificial intelligence, advanced behavioral analysis techniques, and cloud-based architectures.

Towards data fusion-based big data analytics for intrusion detection

ABSTRACT Intrusion detection is seen as the most promising way for computer security. It is used to protect computer networks against different types of attacks. The major problem in the literature is the classification of data into two main classes: normal and intrusion. To solve this problem, several approaches have been proposed but the problem of false alarms is still present. To provide a solution to this problem, we have proposed a new intrusion detection approach based on data fusion. The main objective of this work is to suggest an approach of data fusion-based Big Data analytics to detect intrusions; It is to build one dataset which combines various datasets and contains all the attack types. This research consists in merging the heterogeneous datasets and removing redundancy information using Big Data analytics tools: Hadoop/MapReduce and Neo4j. In the next step, machine learning algorithms are implemented for learning. The first algorithm, called SSDM (Semantically Similar Data Miner), uses fuzzy logic to generate association rules between the different item sets. The second algorithm, called K2, is a score-based greedy search algorithm for learning Bayesian networks from data. Experimentation results prove that – in both cases – data fusion contributes to having very good results.

Superposition Modulation for Physical Layer Security in Water-to-Air Visible Light Communication Systems

In this paper, we propose a physical layer security (PLS) scheme based on superposition modulation for water-to-air (W2A) visible light communication (VLC) systems. We characterize the high correlation between W2A and air-to-water (A2W) link gains from ray tracing simulation and experiments. The proposed scheme selects the modulation order and superposition parameter based on the high correlation between the W2A and A2W link gains. The scheme performance is studied by exploring its immunity against different types of attacks. The symbol error rates (SERs) are analyzed for both random and correlated attacks. Based on the link gains from real measurements, it is shown that under random attack Eve's SER exceeds 0.77 when Eve's signal-to-noise ratio (SNR) varies from 5 dB to 30 dB, and under correlated attack Eve's SER decreases only for a high correlation coefficient when Eve is close enough to Bob, which is unrealistic for eavesdropping. In addition, the entropy of potential set under post-processing attack is derived and the complexity of successful cracking increases with the modulation set size. For intelligent attack, two unsupervised algorithms, namely K-means clustering and expectation maximization (EM) algorithm, are adopted for modulation identification. The distributions of Eve' SER under all four attacks are investigated based on the measured link gains in the laboratory environment, which demonstrates that intelligent attack with K-means clustering possesses the highest eavesdropping capability. However, more numerical results show that for intelligent attack with K-means clustering under wavy water surface, the proportion of the case where Eve has a higher SER than Bob is lower than 0.5 only when Eve lies between Alice and Bob with small horizontal distance, which is unrealistic for eavesdropping operation.

Online Change of Grade Attack Using SQL Injection Case Study: FUTA Cyber Security Department

Advancement in technology has made many universities to adopt the system of storing students' results in online databases in both developed and developing countries for easy accessibility and to eliminate redundancy. However, these are subject to different types of attacks ranging from hardware to software attacks. In Federal University of Technology Akure (FUTA), Cyber Security department is not left out because attackers contribute a potential threat to the institution's information security. There are various methods attackers can use to carry out this malicious act, but this research considered SQL injection attacks. The researcher reviews related works, designs and implements student database applications for FUTA Cyber Security department. The research demonstrates how SQL injection can be used to change student grades and preventive measures to minimize SQL injection attacks, such as avoiding sharing database accounts using different sites or applications, regular updates of database software, regular update of security patches and passwords and regular scanning of web applications with a web vulnerability scanner.

Using High-Level Representation Difference Constraint and Relative Reconstruction Constraint for Defending against Adversarial Attacks

Adversarial examples in which imperceptible perturbations to the input can easily subvert a well-trained model’s prediction pose huge potential security threats to deep neural networks (DNNs). As an effective way to resist adversarial samples, input reconstruction can eliminate the antagonism of adversarial examples in the inference process without involving modifications to the target model’s structure and parameters. However, preprocessing inputs often results in some loss of the protected model’s prediction accuracy. In this paper, we introduce a new input reconstruction method that adopts the high-level representation difference constraint and the relative reconstruction constraint on a dual autoencoder to advance the prediction accuracy of the protected model. The high-level representation difference constraint utilizes the gap between the protected model’s high-level representations, activated by clean images, and their adversarial examples to guide the training of the dual autoencoder. Additionally, the relative reconstruction constraint is imposed on latent representations and their noisy versions to advance the robustness of the dual autoencoder to tiny perturbations. The extensive empirical experiments on two real datasets, CIFAR-10 and ImageNet, show that the presented approach demonstrates exceptional performance in resisting different types of attacks.

Binary Chimp Optimization Algorithm with ML Based Intrusion Detection for Secure IoT-Assisted Wireless Sensor Networks.

An Internet of Things (IoT)-assisted Wireless Sensor Network (WSNs) is a system where WSN nodes and IoT devices together work to share, collect, and process data. This incorporation aims to enhance the effectiveness and efficiency of data analysis and collection, resulting in automation and improved decision-making. Security in WSN-assisted IoT can be referred to as the measures initiated for protecting WSN linked to the IoT. This article presents a Binary Chimp Optimization Algorithm with Machine Learning based Intrusion Detection (BCOA-MLID) technique for secure IoT-WSN. The presented BCOA-MLID technique intends to effectively discriminate different types of attacks to secure the IoT-WSN. In the presented BCOA-MLID technique, data normalization is initially carried out. The BCOA is designed for the optimal selection of features to improve intrusion detection efficacy. To detect intrusions in the IoT-WSN, the BCOA-MLID technique employs a class-specific cost regulation extreme learning machine classification model with a sine cosine algorithm as a parameter optimization approach. The experimental result of the BCOA-MLID technique is tested on the Kaggle intrusion dataset, and the results showcase the significant outcomes of the BCOA-MLID technique with a maximum accuracy of 99.36%, whereas the XGBoost and KNN-AOA models obtained a reduced accuracy of 96.83% and 97.20%, respectively.

A novel hybrid hunger games algorithm for intrusion detection systems based on nonlinear regression modeling.

Along with the advancement of online platforms and significant growth in Internet usage, various threats and cyber-attacks have been emerging and become more complicated and perilous in a day-by-day base. Anomaly-based intrusion detection systems (AIDSs) are lucrative techniques for dealing with cybercrimes. As a relief, AIDS can be equipped with artificial intelligence techniques to validate traffic contents and tackle diverse illicit activities. A variety of methods have been proposed in the literature in recent years. Nevertheless, several important challenges like high false alarm rates, antiquated datasets, imbalanced data, insufficient preprocessing, lack of optimal feature subset, and low detection accuracy in different types of attacks have still remained to be solved. In order to alleviate these shortcomings, in this research a novel intrusion detection system that efficiently detects various types of attacks is proposed. In preprocessing, Smote-Tomek link algorithm is utilized to create balanced classes and produce a standard CICIDS dataset. The proposed system is based on gray wolf and Hunger Games Search (HGS) meta-heuristic algorithms to select feature subsets and detect different attacks such as distributed denial of services, Brute force, Infiltration, Botnet, and Port Scan. Also, to improve exploration and exploitation and boost the convergence speed, genetic algorithm operators are combined with standard algorithms. Using the proposed feature selection technique, more than 80 percent of irrelevant features are removed from the dataset. The behavior of the network is modeled using nonlinear quadratic regression and optimized utilizing the proposed hybrid HGS algorithm. The results show the superior performance of the hybrid algorithm of HGS compared to the baseline algorithms and the well-known research. As shown in the analogy, the proposed model obtained an average test accuracy rate of 99.17%, which has better performance than the baseline algorithm with 94.61% average accuracy.

A Robust Fuzzy Equilibrium Optimization-Based ROI Selection and DWT-Based Multi-Watermarking Model for Medical Images

Image watermarking is the process of securely embedding a higher amount of information in the host object. These processes ensure authentication, image integration, and content verification. Several existing methods face complicated problems, such as security issues, robustness, and data leakage. Therefore, researchers developed specific methods for different applications. However, the performance of the currently obtained method was lower due to their low resistances. Therefore, to overcome this issue, we employed a novel technique, a fuzzy equilibrium optimization (FEO) approach, for embedding water image encryption. Initially, the raw image undergoes fuzzification to determine the critical point; thus, the intensity of the radial line selects a region of interest (ROI). Finally, the watermarking images are converted into a time-frequency domain via discrete wavelet transform (DWT), where the sub-band is converted based on value of magnitude. The proposed technique is analyzed using three medical image datasets, namely magnetic resonance imaging (MRI), ultrasound (US), and computed tomography (CT) datasets. However, all pixels in each sub-band are replaced to form a fully encrypted image, guaranteeing a watermarked reliable, secure, non-breakable format. Singular values are obtained for the encrypted watermarking image to provide high robustness to the watermarked image. After validation, the proposed fuzzy equilibrium optimization technique achieved higher robustness and security against different types of attacks. Moreover, the proposed FEO technique achieved a value of peak signal to noise ratio (PSNR) about 42.5 dB higher than other compared techniques.

An Intrusion Detection System for Drone Swarming Utilizing Timed Probabilistic Automata

Unmanned aerial vehicles (UAVs), commonly known as drones, have found extensive applications across diverse sectors, such as agriculture, delivery, surveillance, and military. In recent times, drone swarming has emerged as a novel field of research, which involves multiple drones working in collaboration towards a shared objective. This innovation holds immense potential in transforming the way we undertake tasks, including military operations, environmental monitoring, and search and rescue missions. However, the emergence of drone swarms also brings new security challenges, as they can be susceptible to hacking and intrusion. To address these concerns, we propose utilizing a timed probabilistic automata (TPA)-based intrusion detection system (IDS) to model the normal behavior of drone swarms and identify any deviations that may indicate an intrusion. This IDS system is particularly efficient and adaptable in detecting different types of attacks in drone swarming. Its ability to adapt to evolving attack patterns and identify zero-day attacks makes it an invaluable tool in protecting drone swarms from malicious attacks.

A survey on security and policy aspects of blockchain technology

This survey talks about the problem of security and privacy in the blockchain ecosystem which is currently a hot issue in the blockchain community. The survey intended to study this problem by considering different types of attacks in the blockchain network with respect to algorithms presented. After a preliminary literature review it seems that some focus has been given to study the first use case while, to the best of my knowledge, the second use case requires more attention when blockchain is applied to study it. The research is also interested in exploring the link between these two use cases to study the overall data ownership preserving accountable system which will be a novel contribution of this work. However, due to the subsequent government mandated secrecy around the implementation of d ata encryption standard ( DES), and the distrust of the academic community because of this, a movement was spawned that put a premium on individual privacy and decentralized control. This movement brought together the top minds in encryption and spawned the technology we know of as blockchain today. This survey explores the genesis of encryption, its early adoption, and the government meddling which eventually spawned a movement which gave birth to the ideas behind blockchain.

IDS-INT: Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

A network intrusion detection system is critical for cyber security against illegitimate attacks. In terms of feature perspectives, network traffic may include a variety of elements such as attack reference, attack type, a sub-category of attack, host information, malicious scripts, etc. In terms of network perspectives, network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic. It is challenging to identify a specific attack due to complex features and data imbalance issues. To address these issues, this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic (IDS-INT). IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data. First, detailed information about each type of attack is gathered from network interaction descriptions, which include network nodes, attack type, reference, host information, etc. Second, the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors. Third, the Synthetic Minority Oversampling Technique (SMOTE) is implemented to balance abnormal traffic and detect minority attacks. Fourth, the Convolution Neural Network (CNN) model is designed to extract deep features from the balanced network traffic. Finally, the hybrid approach of the CNN-Long Short-Term Memory (CNN-LSTM) model is developed to detect different types of attacks from the deep features. Detailed experiments are conducted to test the proposed approach using three standard datasets, i.e., UNSW-NB15, CIC-IDS2017, and NSL-KDD. An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.