Biblio

Injection attack is one of the best 10 security dangers declared by OWASP. SQL infusion is one of the main types of attack. In light of their assorted and quick nature, SQL injection can detrimentally affect the line, prompting broken and public data on the site. Therefore, this article presents a profound woodland-based technique for recognizing complex SQL attacks. Research shows that the methodology we use resolves the issue of expanding and debasing the first condition of the woodland. We are currently presenting the AdaBoost profound timberland-based calculation, which utilizes a blunder level to refresh the heaviness of everything in the classification. At the end of the day, various loads are given during the studio as per the effect of the outcomes on various things. Our model can change the size of the tree quickly and take care of numerous issues to stay away from issues. The aftereffects of the review show that the proposed technique performs better compared to the old machine preparing strategy and progressed preparing technique.

In recent years, insider threat incidents and losses of companies or organizations are on the rise, and internal network security is facing great challenges. Traditional intrusion detection methods cannot identify malicious behaviors of insiders. As an effective method, insider threat detection technology has been widely concerned and studied. In this paper, we use the tree structure method to analyze user behavior, form feature sequences, and combine the Copula Based Outlier Detection (COPOD) method to detect the difference between feature sequences and identify abnormal users. We experimented on the insider threat dataset CERT-IT and compared it with common methods such as Isolation Forest.

Network traffic analysis and deep packet inspection are time-consuming tasks, which current processors can not handle at 100 Gbps speed. Therefore security systems need fast packet processing with hardware acceleration. With the growing of encrypted network traffic, it is necessary to extend Intrusion Detection Systems (IDSes) and other security tools by new detection methods. Security tools started to use classifiers trained by machine learning techniques based on decision trees. Random Forest, Compact Random Forest and AdaBoost provide excellent result in network traffic analysis. Unfortunately, hardware architectures for these machine learning techniques need high utilisation of on-chip memory and logic resources. Therefore we propose several optimisations of highly pipelined architecture for acceleration of machine learning techniques based on decision trees. The optimisations use the various encoding of a feature vector to reduce hardware resources. Due to the proposed optimisations, it was possible to reduce LUTs by 70.5 % for HTTP brute force attack detection and BRAMs by 50 % for application protocol identification. Both with only negligible impact on classifiers' accuracy. Moreover, proposed optimisations reduce wires and multiplexors in the processing pipeline, positively affecting the proposed architecture's maximal achievable frequency.

In the present scenario, security is the biggest concern in any domain of applications. The latest and widely used system for user authentication is a biometric system. This includes fingerprint recognition, retina recognition, and voice recognition. But these systems can be bypassed by masqueraders. To avoid this, a combination of these systems is used which becomes very costly. To overcome these two drawbacks keystroke dynamics were introduced in this field. Keystroke dynamics is a biometric authentication-based system on behavior, which is an automated method in which the identity of an individual is identified and confirmed based on the way and the rhythm of passwords typed on a keyboard by the individual. The work in this paper focuses on identifying the best algorithm for implementing an authentication system with the help of machine learning for user identification based on keystroke dynamics. Our proposed model which uses XGBoost gives a comparatively higher accuracy of 93.59% than the other algorithms for the dataset used.

MIL-STD-1553 is a military standard that defines the specification of a serial communication bus that has been implemented in military and aerospace avionic platforms for over 40 years. MIL-STD-1553 was designed for a high level of fault tolerance while less attention was paid to cyber security issues. Thus, as indicated in recent studies, it is exposed to various threats. In this article, we suggest enhancing the security of MIL-STD-1553 communication buses by integrating a machine learning-based intrusion detection system (IDS); such anIDS will be capable of detecting cyber attacks in real time. The IDS consists of two modules: 1) a remote terminal (RT) authentication module that detects illegitimately connected components and data transfers and 2) a sequence-based anomaly detection module that detects anomalies in the operation of the system. The IDS showed high detection rates for both normal and abnormal behavior when evaluated in a testbed using real 1553 hardware, as well as a very fast and accurate training process using logs from a real system. The RT authentication module managed to authenticate RTs with +0.99 precision and +0.98 recall; and detect illegitimate component (or a legitimate component that impersonates other components) with +0.98 precision and +0.99 recall. The sequence-based anomaly detection module managed to perfectly detect both normal and abnormal behavior. Moreover, the sequencebased anomaly detection module managed to accurately (i.e., zero false positives) model the normal behavior of a real system in a short period of time ( 22 s).

Existing consumer devices represent the most pervasive computational platform available, but their inherently decentralized nature poses significant challenges for distributed computing adoption. In particular, device owners must willingly cooperate in collective deployments even while others may intentionally work to maliciously disrupt that cooperation. Public, cooperative systems benefit from low barriers to entry improving scalability and adoption, but simultaneously increase risk exposure to adversarial threats via promiscuous participant adoption. In this work, I aim to facilitate widespread adoption of cooperative systems by discussing the unique security and operational challenges of these systems, and highlighting several novel approaches that mitigate these disadvantages.

Ciphertext policy Attribute-based encryption (CPABE) plays an increasingly important role in the field of fine-grained access control for cloud storage. However, The exiting solution can not balance the issue of user identity tracking and user revocation. In this paper, we propose a CP-ABE scheme that supports association revocation and traceability. This scheme uses identity directory technology to realize single user revocation and associated user revocation, and the ciphertext re-encryption technology guarantees the forward security of revocation without updating the private key. In addition, we can accurately trace the identity of the user according to the decryption private key and effectively solve the problem of key abuse. This scheme is proved to be safe and traceable under the standard model, and can effectively control the computational and storage costs while maintaining functional advantages. It is suitable for the practical scenarios of tracking audit and user revocation.

Considering the amount of time we spend on the internet, web pages have evolved over a period of time with rapid progression and momentum. With such advancement, we find ourselves fronting a few hostile ideologies, breaching the security levels of webpages as such. The most hazardous of them all is XSS, known as Cross-Site Scripting, is one of the attacks which frequently occur in website-based applications. Cross-Site Scripting (XSS) attacks happen when malicious data enters a web application through an untrusted source. The spam attacks happen in the form of Wall posts, News feed, Message spam and mostly when a user is open to download content of webpages. This paper investigates the use of machine learning to build classifiers to allow the detection of XSS. Establishing our approach, we target the detection modus operandi of XSS attack via two features: URLs and JavaScript. To predict the level of XSS threat, we will be using four machine learning algorithms (SVM, KNN, Random forest and Logistic Regression). Proposing these classified algorithms, webpages will be branded as malicious or benign. After assessing and calculating the dataset features, we concluded that the Random Forest Classifier performed most accurately with the lowest False Positive Rate of 0.34. This precision will ensure a method much efficient to evaluate threatening XSS for the smooth functioning of the system.

Jamming attacks target a wireless network creating an unwanted denial of service. 5G is vulnerable to these attacks despite its resilience prompted by the use of millimeter wave bands. Over the last decade, several types of jamming detection techniques have been proposed, including fuzzy logic, game theory, channel surfing, and time series. Most of these techniques are inefficient in detecting smart jammers. Thus, there is a great need for efficient and fast jamming detection techniques with high accuracy. In this paper, we compare the efficiency of several machine learning models in detecting jamming signals. We investigated the types of signal features that identify jamming signals, and generated a large dataset using these parameters. Using this dataset, the machine learning algorithms were trained, evaluated, and tested. These algorithms are random forest, support vector machine, and neural network. The performance of these algorithms was evaluated and compared using the probability of detection, probability of false alarm, probability of miss detection, and accuracy. The simulation results show that jamming detection based random forest algorithm can detect jammers with a high accuracy, high detection probability and low probability of false alarm.

The decisions made by machines are increasingly comparable in predictive performance to those made by humans, but these decision making processes are often concealed as black boxes. Additional techniques are required to extract understanding, and one such category are explanation methods. This research compares the explanations of two popular forms of artificial intelligence; neural networks and random forests. Researchers in either field often have divided opinions on transparency, and comparing explanations may discover similar ground truths between models. Similarity can help to encourage trust in predictive accuracy alongside transparent structure and unite the respective research fields. This research explores a variety of simulated and real-world datasets that ensure fair applicability to both learning algorithms. A new heuristic explanation method that extends an existing technique is introduced, and our results show that this is somewhat similar to the other methods examined whilst also offering an alternative perspective towards least-important features.

Power systems become a primary target of cyber attacks because of the vulnerability of the integrated communication networks. An attacker is able to manipulate the integrity of real-time data by maliciously modifying the readings of meters transmitted to the control center. Moreover, it is demonstrated that such attack can escape the bad data detection in state estimation if the topology and network information of the entire power grid is known to the attacker. In this paper, we propose an isolation forest (IF) based detection algorithm as a countermeasure against false data attack (FDA). This method requires no tedious pre-training procedure to obtain the labels of outliers. In addition, comparing with other algorithms, the IF based detection method can find the outliers quickly. The performance of the proposed detection method is verified using the simulation results on the IEEE 118-bus system.

K-nearest neighbor (kNN) search has wide applications in many areas, including data mining, machine learning, statistics and many applied domains. Inspired by the success of ensemble methods and the flexibility of tree-based methodology, we propose random projection forests, rpForests, for kNN search. rpForests finds kNNs by aggregating results from an ensemble of random projection trees with each constructed recursively through a series of carefully chosen random projections. rpForests achieves a remarkable accuracy in terms of fast decay in the missing rate of kNNs and that of discrepancy in the kNN distances. rpForests has a very low computational complexity. The ensemble nature of rpForests makes it easily run in parallel on multicore or clustered computers; the running time is expected to be nearly inversely proportional to the number of cores or machines. We give theoretical insights by showing the exponential decay of the probability that neighboring points would be separated by ensemble random projection trees when the ensemble size increases. Our theory can be used to refine the choice of random projections in the growth of trees, and experiments show that the effect is remarkable.

The recognition of intrusions has increased impressive enthusiasm for information mining with the acknowledgment that anomalies can be the key disclosure to be produced using extensive network databases. Intrusions emerge because of different reasons, for example, mechanical deficiencies, changes in framework conduct, fake conduct, human blunder and instrument mistake. Surely, for some applications the revelation of Intrusions prompts more intriguing and helpful outcomes than the disclosure of inliers. Discovery of anomalies can prompt recognizable proof of framework blames with the goal that executives can take preventive measures previously they heighten. A network database framework comprises of a sorted out posting of pages alongside programming to control the network information. This database framework has been intended to empower network operations, oversee accumulations of information, show scientific outcomes and to get to these information utilizing networks. It likewise empowers network clients to gather limitless measure of information on unbounded territories of utilization, break down it and return it into helpful data. Network databases are ordinarily used to help information control utilizing dynamic capacities on sites or for putting away area subordinate data. This database holds a surrogate for each network route. The formation of these surrogates is called ordering and each network database does this errand in an unexpected way. In this paper, a structure for compelling access control and Intrusion Detection using outliers has been proposed and used to give viable Security to network databases. The design of this framework comprises of two noteworthy subsystems to be specific, Access Control Subsystem and Intrusion Detection Subsystem. In this paper preprocessing module is considered which clarifies the preparing of preprocessing the accessible information. And rain forest method is discussed which is used for intrusion detection.

Internet of Things is realized by a large number of heterogeneous smart devices which sense, collect and share data with each other over the internet in order to control the physical world. Due to open nature, global connectivity and resource constrained nature of smart devices and wireless networks the Internet of Things is susceptible to various routing attacks. In this paper, we purpose an architecture of Ensemble Learning based Network Intrusion Detection System named ELNIDS for detecting routing attacks against IPv6 Routing Protocol for Low-Power and Lossy Networks. We implement four different ensemble based machine learning classifiers including Boosted Trees, Bagged Trees, Subspace Discriminant and RUSBoosted Trees. To evaluate proposed intrusion detection model we have used RPL-NIDDS17 dataset which contains packet traces of Sinkhole, Blackhole, Sybil, Clone ID, Selective Forwarding, Hello Flooding and Local Repair attacks. Simulation results show the effectiveness of the proposed architecture. We observe that ensemble of Boosted Trees achieve the highest Accuracy of 94.5% while Subspace Discriminant method achieves the lowest Accuracy of 77.8 % among classifier validation methods. Similarly, an ensemble of RUSBoosted Trees achieves the highest Area under ROC value of 0.98 while lowest Area under ROC value of 0.87 is achieved by an ensemble of Subspace Discriminant among all classifier validation methods. All the implemented classifiers show acceptable performance results.

In recent time it has become very crucial for the data center networks (DCN) to broaden the system limit to be able to meet with the increasing need of cloud based applications. A decent DCN topology must comprise of numerous properties for low diameter, high bisection bandwidth, ease of organization and so on. In addition, a DCN topology should depict aptness in failure resiliency, scalability, construction and routing. In this paper, we introduce a new Data Center Network topology termed LevelTree built up with several modules grows as a tree topology and each module is constructed from a complete graph. LevelTree demonstrates great topological properties and it beats critical topologies like Jellyfish, VolvoxDC, and Fattree regarding providing a superior worthwhile plan with greater capacity.

Web-based social networks enable new community-based opportunities for participants to engage, share their thoughts, and interact with each other. Theses related activities such as searching and advertising are threatened by spammers, content polluters, and malware disseminators. We propose a scalable spam detection system, termed Oases, for uncovering social spam in social networks using an online and scalable approach. The novelty of our design lies in two key components: (1) a decentralized DHT-based tree overlay deployment for harvesting and uncovering deceptive spam from social communities; and (2) a progressive aggregation tree for aggregating the properties of these spam posts for creating new spam classifiers to actively filter out new spam. We design and implement the prototype of Oases and discuss the design considerations of the proposed approach. Our large-scale experiments using real-world Twitter data demonstrate scalability, attractive load-balancing, and graceful efficiency in online spam detection for social networks.

Anti-virus vendors receive hundreds of thousands of malware to be analysed each day. Some are new malware while others are variations or evolutions of existing malware. Because analyzing each malware sample by hand is impossible, automated techniques to analyse and categorize incoming samples are needed. In this work, we explore various machine learning features extracted from malware samples through static analysis for classification of malware binaries into already known malware families. We present a new feature based on control statement shingling that has a comparable accuracy to ordinary opcode n-gram based features while requiring smaller dimensions. This, in turn, results in a shorter training time.

Today, web browsers are a major avenue for cyber-compromise and data breaches. Web browser hardening, through high-granularity and least privilege tailored configurations, can help prevent or mitigate many of these attack avenues. For example, on a classic client desktop infrastructure, an enforced configuration that enables users to use one browser to connect to critical and trusted websites and a different browser for un-trusted sites, with the former restricted to trusted sites and the latter with JavaScript and Plugins disabled by default, may help prevent most JavaScript and Plugin-based attacks to critical enterprise sites. However, most organizations, today, still allow web browsers to run with their default configurations and allow users to use the same browser to connect to trusted and un-trusted sites alike. In this article, we present detailed steps for remotely hardening multiple web browsers in a Windows-based enterprise, for Internet Explorer and Google Chrome. We hope that system administrators use this guide to jump-start an enterprise-wide strategy for implementing high-granularity and least privilege browser hardening. This will help secure enterprise systems at the front-end in addition to the network perimeter.

With the progressive development of network applications and software dependency, we need to discover more advanced methods for protecting our systems. Each industry is equally affected, and regardless of whether we consider the vulnerability of the government or each individual household or company, we have to find a sophisticated and secure way to defend our systems. The starting point is to create a reliable intrusion detection mechanism that will help us to identify the attack at a very early stage; otherwise in the cyber security space the intrusion can affect the system negatively, which can cause enormous consequences and damage the system's privacy, security or financial stability. This paper proposes a concise, and easy to use statistical learning procedure, abbreviated NASCA, which is a four-stage intrusion detection method that can successfully detect unwanted intrusion to our systems. The model is static, but it can be adapted to a dynamic set up.

Smartwatches, with motion sensors, are becoming a common utility for users. With the increasing popularity of practical wearable computers, and in particular smartwatches, the security risks linked with sensors on board these devices have yet to be fully explored. Recent research literature has demonstrated the capability of using a smartphone's own accelerometer and gyroscope to infer tap locations; this paper expands on this work to demonstrate a method for inferring smartphone PINs through the analysis of smartwatch motion sensors. This study determines the feasibility and accuracy of inferring user keystrokes on a smartphone through a smartwatch worn by the user. Specifically, we show that with malware accessing only the smartwatch's motion sensors, it is possible to recognize user activity and specific numeric keypad entries. In a controlled scenario, we achieve results no less than 41% and up to 92% accurate for PIN prediction within 5 guesses.

Among most of the cyber attacks that occured, the most drastic are advanced persistent threats. APTs are differ from other attacks as they have multiple phases, often silent for long period of time and launched by adamant, well-funded opponents. These targeted attacks mainly concentrated on government agencies and organizations in industries, as are those involved in international trade and having sensitive data. APTs escape from detection by antivirus solutions, intrusion detection and intrusion prevention systems and firewalls. In this paper we proposes a classification model having 99.8% accuracy, for the detection of APT.

Storage area networking is driving commodity data center switches to support lossless Ethernet (DCB). Unfortunately, to enable DCB for all traffic on arbitrary network topologies, we must address several problems that can arise in lossless networks, e.g., large buffering delays, unfairness, head of line blocking, and deadlock. We propose TCP-Bolt, a TCP variant that not only addresses the first three problems but reduces flow completion times by as much as 70%. We also introduce a simple, practical deadlock-free routing scheme that eliminates deadlock while achieving aggregate network throughput within 15% of ECMP routing. This small compromise in potential routing capacity is well worth the gains in flow completion time. We note that our results on deadlock-free routing are also of independent interest to the storage area networking community. Further, as our hardware testbed illustrates, these gains are achievable today, without hardware changes to switches or NICs.

Botnet detection represents one of the most crucial prerequisites of successful botnet neutralization. This paper explores how accurate and timely detection can be achieved by using supervised machine learning as the tool of inferring about malicious botnet traffic. In order to do so, the paper introduces a novel flow-based detection system that relies on supervised machine learning for identifying botnet network traffic. For use in the system we consider eight highly regarded machine learning algorithms, indicating the best performing one. Furthermore, the paper evaluates how much traffic needs to be observed per flow in order to capture the patterns of malicious traffic. The proposed system has been tested through the series of experiments using traffic traces originating from two well-known P2P botnets and diverse non-malicious applications. The results of experiments indicate that the system is able to accurately and timely detect botnet traffic using purely flow-based traffic analysis and supervised machine learning. Additionally, the results show that in order to achieve accurate detection traffic flows need to be monitored for only a limited time period and number of packets per flow. This indicates a strong potential of using the proposed approach within a future on-line detection framework.

As the ubiquity of smartphones increases we see an increase in the popularity of location based services. Specifically, online social networks provide services such as alerting the user of friend co-location, and finding a user's k nearest neighbors. Location information is sensitive, which makes privacy a strong concern for location based systems like these. We have built one such service that allows two parties to share location information privately and securely. Our system allows every user to maintain and enforce their own policy. When one party, (Alice), queries the location of another party, (Bob), our system uses homomorphic encryption to test if Alice is within Bob's policy. If she is, Bob's location is shared with Alice only. If she is not, no user location information is shared with anyone. Due to the importance and sensitivity of location information, and the easily deployable design of our system, we offer a useful, practical, and important system to users. Our main contribution is a flexible, practical protocol for private proximity testing, a useful and efficient technique for representing location values, and a working implementation of the system we design in this paper. It is implemented as an Android application with the Facebook online social network used for communication between users.

The use of multiple independent spanning trees (ISTs) for data broadcasting in networks provides a number of advantages, including the increase of fault-tolerance, bandwidth and security. Thus, the designs of multiple ISTs on several classes of networks have been widely investigated. In this paper, we give an algorithm to construct ISTs on enhanced hypercubes Qn,k, which contain folded hypercubes as a subclass. Moreover, we show that these ISTs are near optimal for heights and path lengths. Let D(Qn,k) denote the diameter of Qn,k. If n - k is odd or n - k ∈ {2; n}, we show that all the heights of ISTs are equal to D(Qn,k) + 1, and thus are optimal. Otherwise, we show that each path from a node to the root in a spanning tree has length at most D(Qn,k) + 2. In particular, no more than 2.15 percent of nodes have the maximum path length. As a by-product, we improve the upper bound of wide diameter (respectively, fault diameter) of Qn,k from these path lengths.