Attacks In Cloud Research Articles

A joint lightly perturbation and synthesizing optimization attack framework for point cloud perturbation

Due to the inherent characteristic of deep learning models, prior researchers have focused on studying adversarial strategies aimed at uncovering their vulnerabilities. However, these strategies have been primarily been confined to the realm of image processing. When considering 3D vision structures, such as point clouds and meshes, the robustness of learning models also diminishes significantly in the presence of discernible outliers, and these strategies often fail to generalize across different DNN architectures. In this paper, a simple adversarial perturbation and optimization attack framework, Tangent Plane Perturbation and Synthesizing Optimization Attack (TPSOA) is presented. TPSOA provides a point cloud projection direction for point clouds, subtly inducing imperceptible perturbations on their tangent planes. Furthermore, acknowledging the geometry form of adversarial generation and its potential for 3D printing in physical scenarios, we reconstruct the adversarial mesh alongside the adversarial point cloud. A synthesized loss, incorporating both the Sobolev loss and the Chamfer loss, is utilized to optimize the distances between the adversarial generation and ground truth. Through a combination of visualization and quantitative analysis experiments, we validate the imperceptible nature of TPSOA, the necessity of the loss terms, and the magnitude of perturbations. These experiments that TPSOA enables targeted point cloud attacks that are imperceptible and of minor magnitude. In real-world adversarial attack and defense scenarios, as evidenced by both white-box and black-box experiments, the results show that TPSOA surpasses other state-of-the-art adversarial attack models, effectively manipulating a greater number of victim models while maintaining high efficiency, all without compromising its original structural integrity.

A proposed secure framework for protecting cloud-based educational systems from hacking

Educational institutions and users involved in the whole learning process frequently have concerns about the storage and processing of sensitive data and essential apps in the cloud. Security and privacy issues have emerged as a major challenge, limiting cloud computing’s implementation in educational environments. Several users have yet to meet this security challenge, which is linked to the system’s multi-tenancy nature and the outsourcing of resources and data. This study proposes a secure framework for protecting cloud-based educational systems from hacking using a unique encryption technique, as well as a deep learning-based classification for cloud attack detection. Initially, we preprocess the data and extract features using a gray-level covariance matrix (GLCM). Next, we propose a classification based on multiple convolutional neural networks (M−CNN) to detect attacks in the cloud environment. Finally, we propose a modified digital signature algorithm (MDSA) for data encryption and decryption. The proposed technique achieved high security rates, with an accuracy of 97.7%, sensitivity of 96%, specificity of 94.3%, precision of 99.6%, and recall of 97%. Comparative evaluations showed that the proposed mechanism outperformed other encryption techniques. This novel model enhances the security of cloud-based educational systems and promotes users’ confidence in such platforms.

Distributed SDN Security Frameworks: A Survey

Software-Defined Networks (SDN) have recently received much attention and deployment as a new technology that offers more flexibility and efficiency than traditional networks. SDN is a paradigm shift that revolutionizes traditional network design and makes future networks programmable, manageable, and affordable. The use of the SDN in modern networks provides much needed flexibility and transparency to organize and deploy network solutions. It is a new model that separates forwarding & controlling planes, and centralized architecture designed to increase network speed and programming capability. However, from the current security point of view, the SDN still has some problems, especially for the advanced persistent attacks such as the DDOS, the side channel attacks in Clouds, the SDN stack control plane saturation attacks, and the switch flow table exhaustion attacks. Also, the existing SDN-based security systems are constrained by a central framework that provides significant overheads for the control plane, leading to the breakdown of vital control links. In this paper, we will present the vulnerabilities and security threats in the SDN network, define the various approaches to solve these problems, and deploy the SDN securely in the production environments. We will survey existing research on distributed SDN security frameworks, there is a number of security frameworks and applications that have been proposed previously, and each one of them builds on a selection of the SDN characteristics.

Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing.

With the increasing attention in various 3D safety-critical applications, point cloud learning models have been shown to be vulnerable to adversarial attacks. Although existing 3D attack methods achieve high success rates, they delve into the data space with point-wise perturbation, which may neglect the geometric characteristics. Instead, we propose point cloud attacks from a new perspective-the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that correspond to varying certain geometric structures. Specifically, leveraging on graph signal processing, we first adaptively transform the coordinates of points onto the spectral domain via graph Fourier transform (GFT) for compact representation. Then, we analyze the influence of different spectral bands on the geometric structure, based on which we propose to perturb the GFT coefficients via a learnable graph spectral filter. Considering the low-frequency components mainly contribute to the rough shape of the 3D object, we further introduce a low-frequency constraint to limit perturbations within imperceptible high-frequency components. Finally, the adversarial point cloud is generated by transforming the perturbed spectral representation back to the data domain via the inverse GFT. Experimental results demonstrate the effectiveness of the proposed attack in terms of both the imperceptibility and attack success rates.

PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification

With the growth of 3D sensing technology, the deep learning system for 3D point clouds has become increasingly important, especially in applications such as autonomous vehicles where safety is a primary concern. However, there are growing concerns about the reliability of these systems when they encounter noisy point clouds, either occurring naturally or introduced with malicious intent. This paper highlights the challenges of point cloud classification posed by various forms of noise, from simple background noise to malicious adversarial/backdoor attacks that can intentionally skew model predictions. While there's an urgent need for optimized point cloud denoising, current point outlier removal approaches, an essential step for denoising, rely heavily on handcrafted strategies and are not adapted for higher-level tasks, such as classification. To address this issue, we introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models. Using gradient-based attribution analysis, we define a novel concept: point risk. Drawing inspiration from tail risk minimization in finance, we recast the outlier removal process as an optimization problem, named PointCVaR. Extensive experiments show that our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification. A notable feature of our approach is its effectiveness in defending against the latest threat of backdoor attacks in point clouds.

Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack

Deep learning models for point clouds have shown to be vulnerable to adversarial attacks, which have received increasing attention in various safety-critical applications such as autonomous driving, robotics, and surveillance. Existing 3D attack methods generally employ global distance losses to implicitly constrain the point-wise perturbations for optimization. However, these simple losses are quite difficult to accurately measure and restrict the proper 3D geometry as point clouds are highly structured. Although few recent works try to exploit additional shape-aware surface knowledge to globally constrain the point position, they still fail to preserve the detailed point-to-point geometric dependency in different local regions. To this end, in this paper, we propose a novel Multi-grained Geometry-aware Attack (MGA), which explicitly captures the local topology characteristics in different 3D regions for adversarial constraint. Specifically, we first develop multi-scale spectral local filter banks adapting to different 3D object shapes to explore potential geometric structures in local regions. Considering that objects may contain complex geometries, we then extend each filter bank into multi-layer ones to gradually capture the topology contexts of the same region in a coarse-to-fine manner. Hence, the focused local geometric structures will be highlighted in the coefficients calculated by the filtering process. At last, by restricting these coefficients between benign and adversarial samples, our MGA is able to properly measure and preserve the detailed geometry contexts in the whole 3D object with trivial perturbations. Extensive experiments demonstrate that our attack can achieve superior performance on various 3D classification models, with satisfying adversarial imperceptibility and strong resistance to different defense methods.

An integrated SDN framework for early detection of DDoS attacks in cloud computing

Cloud computing is a rapidly advancing technology with numerous benefits, such as increased availability, scalability, and flexibility. Relocating computing infrastructure to a network simplifies hardware and software resource monitoring in the cloud. Software-Defined Networking (SDN)-based cloud networking improves cloud infrastructure efficiency by dynamically allocating and utilizing network resources. While SDN cloud networks offer numerous advantages, they are vulnerable to Distributed Denial-of-Service (DDoS) attacks. DDoS attacks try to stop genuine users from using services and drain network resources to reduce performance or shut down services. However, early-stage detection of DDoS attack patterns in cloud environments remains challenging. Current methods detect DDoS at the SDN controller level, which is often time-consuming. We recommend focusing on SDN switches for early detection. Due to the large volume of data from diverse sources, we recommend traffic clustering and traffic anomalies prediction which is of DDoS attacks at each switch. Furthermore, to consolidate the data from multiple clusters, event correlation is performed to understand network behavior and detect coordinated attack activities. Many existing techniques stay behind for early detection and integration of multiple techniques to detect DDoS attack patterns. In this paper, we introduce a more efficient and effectively integrated SDN framework that addresses a gap in previous DDoS solutions. Our framework enables early and accurate detection of DDoS traffic patterns within SDN-based cloud environments. In this framework, we use Recursive Feature Elimination (RFE), Density Based Spatial Clustering (DBSCAN), time series techniques like Auto Regressive Integrated Moving Average (ARIMA), Lyapunov exponent, exponential smoothing filter, dynamic threshold, and lastly, Rule-based classifier. We have evaluated the proposed RDAER model on the CICDDoS 2019 dataset, that achieved an accuracy level of 99.92% and a fast detection time of 20 s, outperforming existing methods.

Analysis of SQL injection attacks in the cloud and in WEB applications

AbstractCloud computing has revolutionized the way IT industries work. Most modern‐day companies rely on cloud services to accomplish their day‐to‐day tasks. From hosting websites to developing platforms and storing resources, cloud computing has tremendous use in the modern information technology industry. Although an emerging technique, it has many security challenges. In structured query language injection attacks, the attacker modifies some parts of the user query to still sensitive user information. This type of attack is challenging to detect and prevent. In this article, we have reviewed 65 research articles that address the issue of its prevention and detection in cloud and Traditional Networks, of which 11 research articles are related to general cloud attacks, and the rest of the 54 research articles are specifically on web security. Our result shows that Random Forest has an accuracy of 99.8% and a Precision rate of 99.9%, and the worst‐performing model is Multi‐Layer Perceptron (MLP) in the SQLIA Model. For recall value, Random Forest performs best while TensorFlow Linear Classifier performs worst. F1 score is best in Random Forest, while MLP is the most diminutive performer.

Mitigating DDoS attacks in cloud computing using machine learning algorithms

Distributed Denial of Service (DDoS) attacks pose a significant threat to the availability and performance of cloud computing systems. As these attacks continue to evolve in complexity and scale, traditional mitigation techniques may prove insufficient. This research explores the application of machine learning algorithms as an intelligent and adaptive approach to enhance DDoS detection and mitigation in cloud environments.The study leverages the dynamic and scalable nature of cloud computing to implement a robust defence mechanism against DDoS attacks. Machine learning models, such as supervised and unsupervised learning algorithms, are trained on network traffic data to identify patterns indicative of DDoS activity. The proposed system adapts to evolving attack strategies and is capable of real-time analysis, ensuring swift responses to emerging threats.

A Hybrid Logistic Scroll Chaotic Encryption Algorithm for Ensuring the Cloud Security to Counerfeiting the Attacks

Cloud computing is meant for storing the huge data using third party that ensures that confidential data cannot be accessed by the other users. But with rapid growth of technologies, data in the cloud normally increases which questions its security in storing in the cloud. Hence the protecting the cloud data seeks the strong security levels to counterfeit the different cloud attack. In order to achieve the highest level of security for cloud data, this study suggests a powerful encryption technique that combines chaotic scrolls and logistic maps. The proposed model exhibits the following advantages over the other algorithms: 1) High dynamic key generation 2) ability to counterfeit the multiple attacks 3) High randomness encrypted data which can provide more confusion of hacking from the intruder’s insight. To prove the strength of the proposed model, NIST National Institute of Science and Technology (NIST) is used for significant experiments. in which different statistical tests were carried out to prove the strength of the proposed model. The level of security of the suggested model is also evaluated and investigated using formal analysis using Burrows-Abadi-Needham Logic (BAN). The given model is thoroughly verified using both the Profverif tool and AVISPA. In terms of communication costs and unpredictability, the suggested model's randomness has also been contrasted with that of another existing algorithm. Results demonstrates that the proposed model shows its ability to provide more potent protection to the cloud data than the other existing encryption algorithms.

Intrusion Optimal Path Attack detection using ACO for Cloud Computing

As the cloud infrastructure is simultaneously shared by millions of consumers, heinous use of cloud resources are also increasing. It makes ways to attackers to set up attacks by exploiting the vulnerabilities. And obviously, these attacks are leading to severe disasters as innocent consumers are unknowingly sharing cloud resources with harmful attackers. To prevent the occurrence of cloud attacks, attack graph based framework is proposed in this paper. Here, an attack path sketches an attack scenario by a streak of threats ranging in severity rating that shows how popular a particular cloud network service is in comparison. In a dynamic cloud environment, the proposed framework can disclose an optimal attack path thereby preventing cloud attacks. In cloud system the infrastructure is shared by potentially millions of users, which benefits the attackers to exploit vulnerabilities of the cloud. An instrument for analyzing multi-stage, multi-host assault scenarios in networks is the attack graph. It might not be possible for the administrator to patch every vulnerability n a large number of assault paths in an attack graph. The administrator might not be able to fix every vulnerability. To identify the most preferred or ideal assault path from a particular attack graph in a setting Ant Colony Optimization (ACO) algorithm is used.

Guarding the Cloud: An Effective Detection of Cloud-Based Cyber Attacks using Machine Learning Algorithms

Cloud computing has gained significant popularity due to its reliability and scalability, making it a compelling area of research. However, this technology is not without its challenges, including network connectivity dependencies, downtime, vendor lock-in, limited control, and most importantly, its vulnerability to attacks. Therefore, guarding the cloud is the objective of this paper, which focuses, in a novel approach, on two prevalent cloud attacks: Distributed Denial-of-service (DDoS) attacks and Man-in-the-Cloud (MitC) computing attacks. To tackle the detection of these malicious activities, machine learning algorithms, namely Decision Trees, Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (KNN), are utilized. Experimental simulations of DDoS and MitC attacks are conducted within a cloud environment, and the resultant data is compiled into a dataset for training and evaluating the machine learning algorithms. The study reveals the effectiveness of these algorithms in accurately identifying and classifying malicious activities, effectively distinguishing them from legitimate network traffic. The finding highlights Decision Trees algorithm with most promising potential of guarding the cloud and mitigating the impact of various cyber threats.

Prevention and detection of DDOS attack in virtual cloud computing environment using Naive Bayes algorithm of machine learning

The popularity of cloud computing, with its incredible scalability and accessibility, has already welcomed a new era of innovation. Consumers who subscribe to a cloud-based service and use the associated pay-as-you-go features have unlimited access to the applications mentioned above and technologies. In addition to lowering prices, this notion also increased the reliability and accessibility of the offerings. One of the most crucial aspects of cloud technology is the on-demand viewing of personal services, which is also one of its most significant advantages. Apps that are cloud-based are available on demand from anywhere in the world at a reduced cost. Although it causes its users pain with safety concerns, cloud computing can thrive because of its fantastic instantaneous services. There are various violations, but they all accomplish something similar, taking the systems offline. Distributed denial of service attacks are among the most harmful forms of online assault. For fast and accurate DDoS (Distributed Denial of Service, distributed denial of service) attack detection. This research introduced the DDOS attack and a method to defend against it, making the system more resistant to such attacks. In this scenario, numerous hosts are used to carrying out a distributed denial of service assault against cloud-based web pages, sending possibly millions or even trillions of packets. It uses an OS like ParrotSec to pave the way for the attack and make it possible. In the last phase, the most effective algorithms, such as Naive Bayes and Random Forest, are used for detection and mitigation. Another major topic was studying the many cyber attacks that can be launched against cloud computing.

Detecting and Preventing of DDoS Attack in Cloud Computing Environment Based on Hybrid Technique (Cloudflare and WAF)

The adoption of cloud computing has revolutionized data storage and processing globally. Nevertheless, the need for a close watch on security is paramount. Hence, the aim of this paper, to develop a cloud security model that detects and prevents the risks of Distributed Denial of Service (DDoS) attacks in cloud computing systems which are gravely potent and, on the increase, today. This was done using two approaches: analyzing Transmission Control Protocol/Internet Protocol (TCP/IP) header features of incoming packets in cloud computing environment in order to detect and classify spoofed IP address during DDoS attack via a custom-made Web Application Firewall (WAF); and the integration of the cloud resources with Cloudflare. The result shows that a total of 1,625,192 packets were transmitted in a short period which were captured and analyzed via Wireshark. Several TCP errors were observed over a very short time interval which indicated successful DDoS attack effectively crashing the system. The result varied when the custom-made WAF was put in place, and the attacking lab machine launched a TCP syn flood attack against the web server on port http port 80. A total of 2,353,585 packets were transmitted in a short period which were captured and analyzed using Wireshark and contained less TCP errors indicating successful mitigation of DDoS attacks. When the resources were hosted online and integrated with Cloudflare, integrity checks were successful before the resources were loaded, indicating complete mitigation of attacks. Keywords: Bandwidth, Botnet, Cloudflare, Wireshark and Zombie

Understanding and Mitigating Cloud Computing Security Attacks: A Case of DDoS

Although cloud computing is considered the most widespread technology. Despite of what it offers, the end users still suffers many challenges, especially related to its security issues such as vulnerability to malicious attacks such as Distributed Denial of Service attack (DDoS), that prevents accessing the internet. This paper is design to bring understanding and ways of mitigating DDoS attacks in cloud computing environment by leveraging from the pool of diverse solutions proffered that detect and prevent such attacks from harming network communication. Keywords: Cloudflare, Firewall, Gateway, Webserver and Zombies

Class Based Dynamic Feature Centric Data De-duplication Scheme for Efficient Mitigation of Side Channel Attack in Cloud

Class Based Dynamic Feature Centric Data De-duplication Scheme for Efficient Mitigation of Side Channel Attack in Cloud

Supervised learning for Attack Detection in Cloud

In this study, we approach a supervised learning algorithm to detect attacks in cloud computing. We categorize “Normal” and “Attack” statuses on the dataset. The model evaluation process uses the kappa statistic, the F1-score, recall, accuracy, and precision. The system has a very high detection and efficiency rate, with a detection rate of over 99%. A total of 9594 cases and 44 distinct columns are included in the dataset. The study's results were displayed using a ROC curve and a confusion matrix. This study focuses on implementing a supervised learning algorithm for detecting attacks in cloud computing environments. The main objective is distinguishing between "Normal" and "Attack" statuses based on a carefully curated dataset. Several metrics, such as the kappa statistic, F1-score, recall, accuracy, and precision, are employed to evaluate the model's performance. The dataset utilized in this research comprises 9594 cases and encompasses 44 distinct columns, each representing specific features relevant to cloud computing security. Through a rigorous evaluation process, the algorithm demonstrates exceptional efficiency, achieving a remarkable detection rate of over 99%. Such high accuracy in identifying attacks is crucial for ensuring the integrity and security of cloud-based systems. The significance of this study lies in its successful application of a supervised learning approach to tackle cloud computing security challenges effectively. The model's high detection rate and efficiency indicate its potential for real-world deployment in cloud-based systems, contributing to enhanced threat detection and mitigation. These results hold promising implications for bolstering the security measures of cloud computing platforms and safeguarding sensitive data and services from potential attacks.

SPMAC: Secure and privacy-preserving multi-authority access control for fog-enabled IoT cloud storage

The fog computing paradigm extends the storage, network and computing facilities of the Internet of Things (IoT) to the edge of the network and provides increased convenience in real life. However, IoT still faces great security challenges, such as unauthorized access, collusion attacks between users, cloud attack, and privacy leaks. Most recently, Xiong et al. proposed a scheme to attempt to solve these issues (Xiong et al., 2020). However, we found that their scheme still could not resist the collusion attacks between non-revoked users and revoked users. This study performs the security analysis of SEM-ACSIT and proposes a secure and privacy-preserving multi-authority access control scheme named SPMAC. The proposed scheme can realize flexible user and attribute revocation. The proposed scheme achieves forward security and backward security. For the resource-limited devices, This scheme csn achieve lightweight computing using online–offline encryption technique, outsourced decryption method, and fog computing. It is worth noting that the scheme proposes a ciphertext update check algorithm, allowing users to confirm whether the ciphertext from the untrusted cloud and the user secret key have been updated. The security analysis shows that the proposed scheme can resist multiple collusion attacks, such as revoked and non-revoked users attack, cloud-users attack, and cloud attack. In addition, we realize the hidden access policy to protect users’ privacy. Finally, the results of simulation experiments indicate that the proposed scheme has great practical significance in the access control of IoT.

An intelligent multiclass deep classifier‐based intrusion detection system for cloud environment

SummaryThe intrusion detection process is considered an efficient mechanism that plays a prominent role in network security. Traditional approaches for attack detection, like signature‐based detection, are easily prone to a new variant of attacks. Hence, the most prominent solution for cloud security attacks is an intrusion detection system through deep learning (DL) techniques. The behavior‐based intrusion detection system has been constructed by depicting the cloud traffic as input attributes. The deep learning technique is preferred to extract and analyze the traffic attributes rather than machine learning. Hence, an unsupervised technique named deep autoencoder (AE) is used to extract a feature in this research work. The resultant features are then classified by three classifiers named convolutional neural network (CNN), recurrent neural network (RNN), and long‐short term memory (LSTM). The designed approach is trained and assessed using a real‐time cloud attack dataset, namely, CICIDS 2018. Experimental results are analyzed using quality metrics such as receiver operating characteristics (ROC) curve, precision, accuracy, recall, and F1‐measure. Also, the performance of the proposed method is analyzed with existing literature. Higher accuracy rates like 99.55%, 94.33%, and 99.08% are attained with CNN, RNN, and LSTM networks, which are comparatively higher than the existing approaches.

A novel‐cascaded ANFIS‐based deep reinforcement learning for the detection of attack in cloud IoT‐based smart city applications

SummaryVast usages of Internet of Things (IoT) devices in various smart applications have laid a foundation for the evolution of modern smart cities. The increasing dependency of smart city applications on communication and information technologies enhances operational efficiency, sustainability, and automation of city services. However, due to the heterogeneous nature of IoT devices, the network faces critical security issues while executing continued network operations and services, particularly by cyber‐attacks. One of the predominant and rampant cyber‐attacks in smart city applications is botnet attacks. Therefore, a novel deep learning model for the detection and isolation of cyber‐attacks is proposed in the cloud IoT‐based smart city applications to protect against such cyber‐attacks. The proposed framework utilizes two different modules to automatically detect and isolate the malicious traffic emanating from compromised IoT devices with more efficiency. Here, two different datasets namely the IoT network intrusion and the ISCX 2012 IDs datasets are utilized for the evaluation of the proposed framework. In the first phase, the compromised device which communicates malicious network traffics through the network is identified using a cascaded adaptive neuro‐fuzzy inference system (CANFIS). After detection, IP address of abnormal traffic is recorded and informed to the system administrator. In the second phase, communication pathways of compromised devices with other normal devices are blocked and the compromised devices are isolated from the network using the modified deep reinforcement learning (MDRL) approach. The analytic result shows that the proposed framework achieves a greater accuracy rate of about 98.7% as compared to other state‐of‐art methods.