Biblio

Network based attacks on ecommerce websites can have serious economic consequences. Hence, anomaly detection in dynamic network traffic has become an increasingly important research topic in recent years. This paper proposes a novel dynamic Graph and sparse Autoencoder based Anomaly Detection algorithm named GAAD. In GAAD, the network traffic over contiguous time intervals is first modelled as a series of dynamic bipartite graph increments. One mode projection is performed on each bipartite graph increment and the adjacency matrix derived. Columns of the resultant adjacency matrix are then used to train a sparse autoencoder to reconstruct it. The sum of squared errors between the reconstructed approximation and original adjacency matrix is then calculated. An online learning algorithm is then used to estimate a Gaussian distribution that models the error distribution. Outlier error values are deemed to represent anomalous traffic flows corresponding to possible attacks. In the experiment, a network emulator was used to generate representative ecommerce traffic flows over a time period of 225 minutes with five attacks injected, including SYN scans, host emulation and DDoS attacks. ROC curves were generated to investigate the influence of the autoencoder hyper-parameters. It was found that increasing the number of hidden nodes and their activation level, and increasing sparseness resulted in improved performance. Analysis showed that the sparse autoencoder was unable to encode the highly structured adjacency matrix structures associated with attacks, hence they were detected as anomalies. In contrast, SVD and variants, such as the compact matrix decomposition, were found to accurately encode the attack matrices, hence they went undetected.

Content Delivery Networks(CDN) is a standout amongst the most encouraging innovations that upgrade performance for its clients' websites by diverting web demands from browsers to topographically dispersed CDN surrogate nodes. However, due to the variable nature of CDN, it suffers from various security and resource allocation issues. The most common attack which is used to bring down a whole network as well as CDN without even finding a loophole in the security is DDoS. In this proposal, we proposed a distributed virtual honeypot model for diminishing DDoS attacks and prevent intrusion in securing CDN. Honeypots are specially utilized to imitate the primary server with the goal that the attack is alleviated to the fake rather than the main server. Our proposed layer based model utilizes honeypot to be more effective reducing the cost of the system as well as maintaining the smooth delivery in geographically dispersed servers without performance degradation.

Distributed Denial of Service(DDoS) attacks have become most important network security threat as the number of devices are connected to internet increases exponentially and reaching an attack volume approximately very high compared to other attacks. To make the network safe and flexible a new networking infrastructure such as Software Defined Networking (SDN) has come into effect, which relies on centralized controller and decoupling of control and data plane. However due to it's centralized controller it is prone to DDoS attacks, as it makes the decision of forwarding of packets based on rules installed in switch by OpenFlow protocol. Out of all different DDoS attacks, UDP (User Datagram Protocol) flooding constitute the most in recent years. In this paper, we have proposed an entropy based DDoS detection and rate limiting based mitigation for efficient service delivery. We have evaluated using Mininet as emulator and Ryu as controller by taking switch as OpenVswitch and obtained better result in terms of bandwidth utilization and hit ratio which consume network resources to make denial of service.

We have been investigating methods for establishing an effective, immediate defense mechanism against the DDoS attacks on Web applications via hacker botnets, in which this defense mechanism can be immediately active without preparation time, e.g. for training data, usually asked for in existing proposals. In this study, we propose a new mechanism, including new data structures and algorithms, that allow the detection and filtering of large amounts of attack packets (Web request) based on monitoring and capturing the suspect groups of source IPs that can be sending packets at similar patterns, i.e. with very high and similar frequencies. The proposed algorithm places great emphasis on reducing storage space and processing time so it is promising to be effective in real-time attack response.

Distributed Denial of Service (DDoS) attacks have been the prominent attacks over the last decade. A Network Intrusion Detection System (NIDS) should seamlessly configure to fight against these attackers' new approaches and patterns of DDoS attack. In this paper, we propose a NIDS which can detect existing as well as new types of DDoS attacks. The key feature of our NIDS is that it combines different classifiers using ensemble models, with the idea that each classifier can target specific aspects/types of intrusions, and in doing so provides a more robust defense mechanism against new intrusions. Further, we perform a detailed analysis of DDoS attacks, and based on this domain-knowledge verify the reduced feature set [27, 28] to significantly improve accuracy. We experiment with and analyze NSL-KDD dataset with reduced feature set and our proposed NIDS can detect 99.1% of DDoS attacks successfully. We compare our results with other existing approaches. Our NIDS approach has the learning capability to keep up with new and emerging DDoS attack patterns.

In the paper is presented implementation of a system for detecting intrusion actions. An implementation of intrusion detection systems (IDS), their architectures, and intrusion detection methods are investigated. Analyzed are methods for SNORT (IDS) bandwidth traffic analysis in intrusion detection and prevention systems. The main requirements for Installation and configuration of the system are also discussed. Then the configuration of the firewall policy and specifics there, are also presented. It is also described the database structure, the operating modes, and analysis of the rules. Two of the most commonly implemented attacks and model for defense against them is proposed.

Internet of Things (IoT) is transforming the way we live today, improving the quality of living standard and growing the world economy by having smart devices around us making decisions and performing our daily tasks and chores. However, securing the IoT system from malicious attacks is a very challenging task. Some of the most common malicious attacks are Denial of service (DoS), and Distributed Denial of service (DDoS) attacks, which have been causing major security threats to all networks and specifically to limited resource IoT devices. As security will always be a primary factor for enabling most IoT applications, developing a comprehensive detection method that effectively defends against DDoS attacks and can provide 100% detection for DDoS attacks in IoT is a primary goal for the future of IoT. The development of such a method requires a deep understanding of the methods that have been used thus far in the detection of DDoS attacks in the IoT environment. In our survey, we try to emphasize some of the most recent Machine Learning (ML) approaches developed for the detection of DDoS attacks in IoT networks along with their advantage and disadvantages. Comparison between the performances of selected approaches is also provided.

Distributed Denial of Services (DDoS) attacks continue to be one of the most challenging threats to the Internet. The intensity and frequency of these attacks are increasing at an alarming rate. Numerous schemes have been proposed to mitigate the impact of DDoS attacks. This paper presents a comprehensive empirical evaluation of Machine Learning (ML)based DDoS detection techniques, to gain better understanding of their performance in different types of environments. To this end, a framework is developed, focusing on different attack scenarios, to investigate the performance of a class of ML-based techniques. The evaluation uses different performance metrics, including the impact of the “Class Imbalance Problem” on ML-based DDoS detection. The results of the comparative analysis show that no one technique outperforms all others in all test cases. Furthermore, the results underscore the need for a method oriented feature selection model to enhance the capabilities of ML-based detection techniques. Finally, the results show that the class imbalance problem significantly impacts performance, underscoring the need to address this problem in order to enhance ML-based DDoS detection capabilities.

Moving target defense (MTD) is becoming popular with the advancements in Software Defined Networking (SDN) technologies. With centralized management through SDN, changing the network attributes such as routes to escape from attacks is simple and fast. Yet, the available alternate routes are bounded by the network topology, and a persistent attacker that continuously perform the reconnaissance can extract the whole link-map of the network. To address this issue, we propose to use virtual shadow networks (VSNs) by applying Network Function Virtualization (NFV) abilities to the network in order to deceive attacker with the fake topology information and not reveal the actual network topology and characteristics. We design this approach under a formal framework for Internet Service Provider (ISP) networks and apply it to the recently emerged indirect DDoS attacks, namely Crossfire, for evaluation. The results show that attacker spends more time to figure out the network behavior while the costs on the defender and network operations are negligible until reaching a certain network size.

As the dynamics of cyber warfare continue to change, it is very important to be aware of the issues currently confronting cyberspace. One threat which continues to grow in the danger it poses to cyber security are botnets. Botnets can launch massive Distributed Denial of Service (DDoS) attacks against internet connected hosts anonymously, undertake intricate spam campaigns, launch mass financial fraud campaigns, and even manipulate public opinion via social media bots. The network topology and technology undergirding each botnet varies greatly, as do the motivations commonly behind such networks. Furthermore, as botnets have continued to evolve, many newer ones demonstrate increased levels of anonymity and sophistication, making it more difficult to effectively counter them. Increases in the production of vulnerable Internet of Things (IoT) devices has made it easier for malicious actors to quickly assemble sizable botnets. Because of this, the steps necessary to stop botnets also vary, and in some cases, it may be extremely difficult to effectively defeat a fully functional and sophisticated botnet. While in some cases, the infrastructure supporting the botnet can be targeted and remotely disabled, other cases require the physical assistance of law enforcement to shut down the botnet. In the latter case, it is often a significant challenge to cheaply end a botnet. On the other hand, there are many steps and mitigations that can be taken by end-users to prevent their own devices from becoming part of a botnet. Many of these solutions involve implementing basic cybersecurity practices like installing firewalls and changing default passwords. More sophisticated botnets may require similarly sophisticated intrusion detection systems, to detect and remove malicious infections. Much research has gone into such systems and in recent years many researchers have begun to implement machine learning techniques to defeat botnets. This paper is intended present a review on botnet evolution, trends and mitigations, and offer related examples and research to provide the reader with quick access to a broad understanding of the issues at hand.

Mitigating the effect of Distributed Denial of Service (DDoS) attacks in wired/wireless networks is a problem of extreme importance. The present paper investigates this problem and proposes a secure AQM to encounter the effects of DDoS attacks on queue's router. The employed method relies on modelling the TCP/AQM system subjected to different DoS attack rate where the resulting closed-loop system is expressed as new Markovian Jump Linear System (MJLS). Sufficient delay-dependent conditions which guarantee the syntheses of a stabilizing control for the closed-loop system with a guaranteed cost J* are derived. Finally, a numerical example is displayed.

This paper presents an experimental analysis of current Distributed Denial of Service attacks. Our analysis is based on real data collected by a honeynet system that was installed on an ISP edge router, for a four-month period. In the examined scenario, we identify and analyze malicious activities based on packets captured and analyzed by a network protocol sniffer and signature-based attack analysis tools. Our analysis shows that IoT-based DDoS attacks are one of the latest and most proliferating attack trends in network security. Based on the analysis of the attacks, we describe some mitigation techniques that can be applied at the providers' network to mitigate the trending attack vectors.

Software-Defined Network's (SDN) core working depends on the centralized controller which implements the control plane. With the help of this controller, security threats like Distributed Denial of Service (DDoS) attacks can be identified easily. A DDoS attack is usually instigated on servers by sending a huge amount of unwanted traffic that exhausts its resources, denying their services to genuine users. Earlier research work has been carried out to mitigate DDoS attacks at the switch and the host level. Mitigation at switch level involves identifying the switch which sends a lot of unwanted traffic in the network and blocking it from the network. But this solution is not feasible as it will also block genuine hosts connected to that switch. Later mitigation at the host level was introduced wherein the compromised hosts were identified and blocked thereby allowing genuine hosts to send their traffic in the network. Though this solution is feasible, it will block the traffic from the genuine applications of the compromised host as well. In this paper, we propose a new way to identify and mitigate the DDoS attack at the application level so that only the application generating the DDoS traffic is blocked and other genuine applications are allowed to send traffic in the network normally.

In today's time Software Defined Network (SDN) gives the complete control to get the data flow in the network. SDN works as a central point to which data is administered centrally and traffic is also managed. SDN being open source product is more prone to security threats. The security policies are also to be enforced as it would otherwise let the controller be attacked the most. The attacks like DDOS and DOS attacks are more commonly found in SDN controller. DDOS is destructive attack that normally diverts the normal flow of traffic and starts the over flow of flooded packets halting the system. Machine Learning techniques helps to identify the hidden and unexpected pattern of the network and hence helps in analyzing the network flow. All the classified and unclassified techniques can help detect the malicious flow based on certain parameters like packet flow, time duration, accuracy and precision rate. Researchers have used Bayesian Network, Wavelets, Support Vector Machine and KNN to detect DDOS attacks. As per the review it's been analyzed that KNN produces better result as per the higher precision and giving a lower falser rate for detection. This paper produces better approach of hybrid Machine Learning techniques rather than existing KNN on the same data set giving more accuracy of detecting DDOS attacks on higher precision rate. The result of the traffic with both normal and abnormal behavior is shown and as per the result the proposed algorithm is designed which is suited for giving better approach than KNN and will be implemented later on for future.

Many enterprises and individuals prefer to outsource data to public cloud via various pricing approaches. One of the most widely-used approaches is the pay-as-you-go model, where the data owner hires public cloud to share data with data consumers, and only pays for the actually consumed services. To realize controllable and secure data sharing, ciphertext-policy attribute-based encryption (CP-ABE) is a suitable solution, which can provide fine-grained access control and encryption functionalities simultaneously. But there are some serious challenges when applying CP-ABE in pay-as-you-go. Firstly, the decryption cost in ABE is too heavy for data consumers. Secondly, ABE ciphertexts probably suffer distributed denial of services (DDoS) attacks, but there is no solution that can eliminate the security risk. At last, the data owner should audit resource consumption to guarantee the transparency of charge, while the existing method is inefficient. In this work, we propose a general construction named fully accountable ABE (FA-ABE), which simultaneously solves all the challenges by supporting all-sided accountability in the pay-as-you-go model. We formally define the security model and prove the security in the standard model. Also, we implement an instantiate construction with the self-developed library libabe. The experiment results indicate the efficiency and practicality of our construction.

In recent years, the attacks on systems have increased and among such attack is Distributed Denial of Service (DDoS) attack. The path identifiers (PIDs) used for inter-domain routing are static, which makes it easier the attack easier. To address this vulnerability, this paper addresses the usage of Dynamic Path Identifiers (D-PIDs) for routing. The PID of inter-domain path connector is kept oblivious and changes dynamically, thus making it difficult to attack the system. The prototype designed with major components like client, server and router analyses the outcome of D-PID usage instead of PIDs. The results show that, DDoS attacks can be effectively prevented if Dynamic Path Identifiers (D-PIDs) are used instead of Static Path Identifiers (PIDs).

The convergence of access networks in the fifth-generation (5G) evolution promises multi-tier networking infrastructures for the successes of various applications realizing the Internet-of-Everything era. However, in this context, the support of a massive number of connected devices also opens great opportunities for attackers to exploit these devices in illegal actions against their victims, especially within the distributed denial-of-services (DDoS) attacks. Nowadays, DDoS prevention still remains an open issue in term of performance improvement although there is a significant number of existing solutions have been proposed in the literature. In this paper, we investigate the advances of multi-access edge computing (MAEC), which is considered as one of the most important emerging technologies in 5G networks, in order to provide an effective DDoS prevention solution (referred to be MAEC-X). The proposed MAEC-X architecture and mechanism are developed as well as proved its effectiveness against DDoS attacks through intensive security analysis.

Software Defined Network (SDN) is a revolutionary idea to realize software-driven network with the separation of control and data planes. In essence, SDN addresses the problems faced by the traditional network architecture; however, it may as well expose the network to new attacks. Among other attacks, distributed denial of service (DDoS) attacks are hard to contain in such software-based networks. Existing DDoS mitigation techniques either lack in performance or jeopardize the accuracy of the attack detection. To fill the voids, we propose in this paper a machine learning-based DDoS mitigation technique for SDN. First, we create a model for DDoS detection in SDN using NSL-KDD dataset and then after training the model on this dataset, we use real DDoS attacks to assess our proposed model. Obtained results show that the proposed technique equates favorably to the current techniques with increased performance and accuracy.

The emergence of Software Defined Network (SDN) and its promises in networking technology has gotten every stakeholder excited. However, it is believed that every technological development comes with its own challenges of which the most prominent in this case is security. This paper presents a real time detection of the distributed denial of service (DDoS) attacks on the SDN and a control method based on the sFlow mitigation technology. sFlow analyses samples of packets collected from the network traffic and generates handling rules to be sent to the controller in case of an attack detection. The implementation was done by emulating the network in Mininet which runs on a Virtual Machine (VM) and it was shown that the proposed method effectively detects and mitigates DDoS attacks.

Vehicular ad hoc networks (VANETs) are eminent type of Mobile ad hoc Networks. The network created in VANETs is quite prone to security problem. In this work, a new mechanism is proposed to study the security of VANETs against DDoS attack. The proposed mechanism focuses on distributed denial of service attacks. The main idea of the paper is to detect the DDoS attack and mitigate it. The work consists of two stages, initially attack topology and network congestion is created. The second stage is to detect and mitigate the DDoS attack. The existing method is compared with the proposed method for mitigating DDoS attacks in VANETs. The existing solutions presented by the various researchers are also compared and analyzed. The solution for such kind of problem is provided which is used to detect and mitigate DDoS attack by using greedy approach. The network environment is created using NS-2. The results of simulation represent that the proposed approach is better in the terms of network packet loss, routing overhead and network throughput.

Underpinning the operation of Bitcoin is a peer-to-peer (P2P) network [1] that facilitates the execution of transactions by end users, as well as the transaction confirmation process known as bitcoin mining. The security of this P2P network is vital for the currency to function and subversion of the underlying network can lead to attacks on bitcoin users including theft of bitcoins, manipulation of the mining process and denial of service (DoS). As part of this paper the network protocol and bitcoin core software are analysed, with three bitcoin message exchanges (the connection handshake, GETHEADERS/HEADERS and MEMPOOL/INV) found to be potentially vulnerable to spoofing and use in distributed denial of service (DDoS) attacks. Possible solutions to the identified weaknesses and vulnerabilities are evaluated, such as the introduction of random nonces into network messages exchanges.

Live VM migration is the most vulnerable process in cloud federations for DDOS attacks, loss of data integrity, confidentiality, unauthorized access and injection of malicious viruses on VM disk images. We have scrutinized following set of crucial security features which are; authorization, confidentiality, replay protection (accountability), integrity, mutual authentication and source non-repudiation (availability) to cater different threats and vulnerabilities during live VM migration. The investigated threats and vulnerabilities are catered and implemented in a proposed solution, presented in this paper. Six security features-authorization, confidentiality, replay protection, integrity, mutual authentication and source non-repudiation are focused and modular implementation has been done. Solution is validated in AVISPA tool in modules for threats for all the notorious security requirements and no outbreak were seen.

Botnet is one of the major threats on the Internet for committing cybercrimes, such as DDoS attacks, stealing sensitive information, spreading spams, etc. It is a challenging issue to detect modern botnets that are continuously improving for evading detection. In this paper, we propose a machine learning based botnet detection system that is shown to be effective in identifying P2P botnets. Our approach extracts convolutional version of effective flow-based features, and trains a classification model by using a feed-forward artificial neural network. The experimental results show that the accuracy of detection using the convolutional features is better than the ones using the traditional features. It can achieve 94.7% of detection accuracy and 2.2% of false positive rate on the known P2P botnet datasets. Furthermore, our system provides an additional confidence testing for enhancing performance of botnet detection. It further classifies the network traffic of insufficient confidence in the neural network. The experiment shows that this stage can increase the detection accuracy up to 98.6% and decrease the false positive rate up to 0.5%.

It is well known that distributed cyber attacks simultaneously launched from many hosts have caused the most serious problems in recent years including problems of privacy leakage and denial of services. Thus, how to detect those attacks at early stage has become an important and urgent topic in the cyber security community. For this purpose, recognizing C&C (Command & Control) communication between compromised bots and the C&C server becomes a crucially important issue, because C&C communication is in the preparation phase of distributed attacks. Although attack detection based on signature has been practically applied since long ago, it is well-known that it cannot efficiently deal with new kinds of attacks. In recent years, ML(Machine learning)-based detection methods have been studied widely. In those methods, feature selection is obviously very important to the detection performance. We once utilized up to 55 features to pick out C&C traffic in order to accomplish early detection of DDoS attacks. In this work, we try to answer the question that "Are all of those features really necessary?" We mainly investigate how the detection performance moves as the features are removed from those having lowest importance and we try to make it clear that what features should be payed attention for early detection of distributed attacks. We use honeypot data collected during the period from 2008 to 2013. SVM(Support Vector Machine) and PCA(Principal Component Analysis) are utilized for feature selection and SVM and RF(Random Forest) are for building the classifier. We find that the detection performance is generally getting better if more features are utilized. However, after the number of features has reached around 40, the detection performance will not change much even more features are used. It is also verified that, in some specific cases, more features do not always means a better detection performance. We also discuss 10 important features which have the biggest influence on classification.

Distributed denial-of-service (DDoS) attack remains an exceptional security risk, alleviating these digital attacks are for all intents and purposes extremely intense to actualize, particularly when it faces exceptionally well conveyed attacks. The early disclosure of these attacks, through testing, is critical to ensure safety of end-clients and the wide-ranging expensive network resources. With respect to DDoS attacks - its hypothetical establishment, engineering, and calculations of a honeypot have been characterized. At its core, the honeypot consists of an intrusion prevention system (Interruption counteractive action framework) situated in the Internet Service Providers level. The IPSs then create a safety net to protect the hosts by trading chosen movement data. The evaluation of honeypot promotes broad reproductions and an absolute dataset is introduced, indicating honeypot's activity and low overhead. The honeypot anticipates such assaults and mitigates the servers. The prevailing IDS are generally modulated to distinguish known authority level system attacks. This spontaneity makes the honeypot system powerful against uncommon and strange vindictive attacks.