Biblio

Various studies have been performed to explore the feasibility of detection of web-based attacks by machine learning techniques. False-positive and false-negative results have been reported as a major issue to be addressed to make machine learning-based detection and prevention of web-based attacks reliable and trustworthy. In our research, we tried to identify and address the root cause of the false-positive and false-negative results. In our experiment, we used the CSIC 2010 HTTP dataset, which contains the generated traffic targeted to an e-commerce web application. Our experimental results demonstrate that applying the proposed fine-tuned feature set extraction results in improved detection and classification of web-based attacks for all tested machine learning algorithms. The performance of the machine learning algorithm in the detection of attacks was evaluated by the Precision, Recall, Accuracy, and F-measure metrics. Among three tested algorithms, the J48 decision tree algorithm provided the highest True Positive rate, Precision, and Recall.

Insider attacks is a well-known problem acknowledged as a threat as early as 1980s. The threat is attributed to legitimate users who take advantage of familiarity with the computational environment and abuse their privileges, can easily cause significant damage or losses. In this paper, we present an active defense model and framework of insider threat detection and sense. Firstly, we describe the hierarchical framework which deal with insider threat from several aspects, and subsequently, show a hierarchy-mapping based insider threats model, the kernel of the threats detection, sense and prediction. The experiments show that the model and framework could sense the insider threat in real-time effectively.

To ensure security, Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is widely used in people's online lives. This paper presents a Chinese character captcha sequential selection system based on convolutional neural network (CNN). Captchas composed of English and digits can already be identified with extremely high accuracy, but Chinese character captcha recognition is still challenging. The task we need to complete is to identify Chinese characters with different colors and different fonts that are not on a straight line with rotation and affine transformation on pictures with complex backgrounds, and then perform word order restoration on the identified Chinese characters. We divide the task into several sub-processes: Chinese character detection based on Faster R-CNN, Chinese character recognition and word order recovery based on N-Gram. In the Chinese character recognition sub-process, we have made outstanding contributions. We constructed a single Chinese character data set and built a 10-layer convolutional neural network. Eventually we achieved an accuracy of 98.43%, and completed the task perfectly.

P2P botnet has become one of the most serious threats to today's network security. It can be used to launch kinds of malicious activities, ranging from spamming to distributed denial of service attack. However, the detection of P2P botnet is always challenging because of its decentralized architecture. In this paper, we propose a two-stage P2P botnet detection method which only relies on several traffic statistical features. This method first detects P2P hosts based on three statistical features, and then distinguishes P2P bots from benign P2P hosts by means of another two statistical features. Experimental evaluations on real-world traffic datasets shows that our method is able to detect hidden P2P bots with a detection accuracy of 99.7% and a false positive rate of only 0.3% within 5 minutes.

Microarchitectural Side-Channel Attacks (SCAs) have emerged recently to compromise the security of computer systems by exploiting the existing processors' hardware vulnerabilities. In order to detect such attacks, prior studies have proposed the deployment of low-level features captured from built-in Hardware Performance Counter (HPC) registers in modern microprocessors to implement accurate Machine Learning (ML)-based SCAs detectors. Though effective, such attack detection techniques have mainly focused on binary classification models offering limited insights on identifying the type of attacks. In addition, while existing SCAs detectors required prior knowledge of attacks applications to detect the pattern of side-channel attacks using a variety of microarchitectural features, detecting unknown (zero-day) SCAs at run-time using the available HPCs remains a major challenge. In response, in this work we first identify the most important HPC features for SCA detection using an effective feature reduction method. Next, we propose Phased-Guard, a two-level machine learning-based framework to accurately detect and classify both known and unknown attacks at run-time using the most prominent low-level features. In the first level (SCA Detection), Phased-Guard using a binary classification model detects the existence of SCAs on the target system by determining the critical scenarios including system under attack and system under no attack. In the second level (SCA Identification) to further enhance the security against side-channel attacks, Phased-Guard deploys a multiclass classification model to identify the type of SCA applications. The experimental results indicate that Phased-Guard by monitoring only the victim applications' microarchitectural HPCs data, achieves up to 98 % attack detection accuracy and 99.5% SCA identification accuracy significantly outperforming the state-of-the-art solutions by up to 82 % in zero-day attack detection at the cost of only 4% performance overhead for monitoring.

Cybercrime is growing dramatically in the technological world nowadays. World Wide Web criminals exploit the personal information of internet users and use them to their advantage. Unethical users leverage the dark web to buy and sell illegal products or services and sometimes they manage to gain access to classified government information. A number of illegal activities that can be found in the dark web include selling or buying hacking tools, stolen data, digital fraud, terrorists activities, drugs, weapons, and more. The aim of this project is to collect evidence of any malicious activity in the dark web by using computer security mechanisms as traps called honeypots.

Tor anonymous communication system's resource publishing is vulnerable to enumeration attacks. Zhao determines users who requested resources are unavailable as suspicious malicious users, and gradually reduce the scope of suspicious users through several stages to reduce the false positive rate. However, it takes several stages to distinguish users. Although this method successfully detects the malicious user, the malicious user has acquired many resources in the previous stages, which reduce the availability of the anonymous communication system. This paper proposes a detection method based on Integer Linear Program to detect malicious users who perform enumeration attacks on resources in the process of resource distribution. First, we need construct a bipartite graph between the unavailable resources and the users who requested for these resources in the anonymous communication system; next we use Integer Linear Program to find the minimum malicious user set. We simulate the resource distribution process through computer program, we perform an experimental analysis of the method in this paper is carried out. Experimental results show that the accuracy of the method in this paper is above 80%, when the unavailable resources in the system account for no more than 50%. It is about 10% higher than Zhao's method.

In the paper, our research of abnormal bus data analysis of intelligent and connected vehicle aims to detect the abnormal data rapidly and accurately generated by the hackers who send malicious commands to attack vehicles through three patterns, including remote non-contact, short-range non-contact and contact. The research routine is as follows: Take the bus data of 10 different brands of intelligent and connected vehicles through the real vehicle experiments as the research foundation, set up the optimized neural network, collect 1000 sets of the normal bus data of 15 kinds of driving scenarios and the other 300 groups covering the abnormal bus data generated by attacking the three systems which are most common in the intelligent and connected vehicles as the training set. In the end after repeated amendments, with 0.5 seconds per detection, the intrusion detection system has been attained in which for the controlling system the abnormal bus data is detected at the accuracy rate of 96% and the normal data is detected at the accuracy rate of 90%, for the body system the abnormal one is 87% and the normal one is 80%, for the entertainment system the abnormal one is 80% and the normal one is 65%.

Ad hoc network is sensitive to attacks because it has temporary nature and frequently recognized insecure environment. Both Ad hoc On-demand Distance Vector (AODV) and Ad hoc On-demand Multipath Distance vector (AOMDV) routing protocols have the strategy to take help from Wireless and mobile ad hoc networks. A mobile ad hoc network (MANET) is recognized as an useful internet protocol and where the mobile nodes are self-configuring and self-organizing in character. This research paper has focused on the detection and influence of black hole attack on the execution of AODV and AOMDV routing protocols and has also evaluated the performance of those two on-demand routing protocols in MANETs. AODV has the characteristics for discovering a single path in single route discovery and AOMDV has the characteristics for discovering multiple paths in single route discovery. Here a proposed method for both AODV and AOMDV routing protocol, has been applied for the detection of the black hole attack, which is the merge of both SHA-3 and Diffie-Hellman algorithm. This merge technique has been applied to detect black hole attack in MANET. This technique has been applied to measure the performance matrices for both AODV and AOMDV and those performance matrices are Average Throughput, Average End to End delay and Normalized Routing Load. Both AODV and AOMDV routing protocol have been compared with each other to show that under black hole attack, AOMDV protocol always has better execution than AODV protocol. Here, NS-2.35 has been used as the Network Simulator tool for the simulation of these particular three types of performance metrics stated above.

Since Bitcoin, the first cryptocurrency that applied blockchain technology was developed by Satoshi Nakamoto, the cryptocurrency market has grown rapidly. Along with this growth, many vulnerabilities and attacks are threatening the Bitcoin ecosystem, which is not only at the bitcoin network-level but also at the service level that applied it, according to the survey. We intend to analyze and detect DDoS attacks on the premise that bitcoin's network-level data and service-level DDoS attacks with bitcoin are associated. We evaluate the results of the experiment according to the proposed metrics, resulting in an association between network-level data and service-level DDoS attacks of bitcoin. In conclusion, we suggest the possibility that the proposed method could be applied to other blockchain systems.

The recent malware outbreaks have shown that the existing end-point security solutions are not robust enough to secure the systems from getting compromised. The techniques, like code obfuscation along with one or more zero-days, are used by malware developers for evading the security systems. These malwares are used for large-scale attacks involving Advanced Persistent Threats(APT), Botnets, Cryptojacking, etc. Cryptojacking poses a severe threat to various organizations and individuals. We are summarising multiple methods available for the detection of malware.

Distributed Denial of Service attacks (DDoS) are used by attackers for their effectiveness. This type of attack is one of the most devastating attacks in the Internet. Every year, the intensity of DDoS attacks increases and attackers use sophisticated multi-target DDoS attacks. In this paper, a modular system that allows to increase the filtering capacity linearly and allows to protect against the combination of DDoS attacks is designed and implemented. The main motivation for development of the modular filtering system was to find a cheap solution for filtering DDoS attacks with possibility to increase filtering capacity. The proposed system is based on open-source detection and filtration tools.

In order to study the application of improved image hashing algorithm in image tampering detection, based on compressed sensing and ring segmentation, a new image hashing technique is studied. The image hash algorithm based on compressed sensing and ring segmentation is proposed. First, the algorithm preprocesses the input image. Then, the ring segment is used to extract the set of pixels in each ring region. These aggregate data are separately performed compressed sensing measurements. Finally, the hash value is constructed by calculating the inner product of the measurement vector and the random vector. The results show that the algorithm has good perceived robustness, uniqueness and security. Finally, the ROC curve is used to analyze the classification performance. The comparison of ROC curves shows that the performance of the proposed algorithm is better than FM-CS, GF-LVQ and RT-DCT.

Face detection is an application widely used in video surveillance systems and it is the first step for subsequent applications such as monitoring and recognition. For facial detection, there are a series of algorithms that allow the face to be extracted in a video image, among which are the Viola & Jones waterfall method and the method by geometric models using the Hausdorff distance. In this article, both algorithms are theoretically analyzed and the best one is determined by efficiency and resource optimization. Considering the most common problems in the detection of faces in a video surveillance system, such as the conditions of brightness and the angle of rotation of the face, tests have been carried out in 13 different scenarios with the best theoretically analyzed algorithm and its combination with another algorithm The images obtained, using a digital camera in the 13 scenarios, have been analyzed using Matlab code of the Viola & Jones and Viola & Jones algorithm combined with the Kanade-Lucas-Tomasi algorithm to add the feature of completing the tracking of a single object. This paper presents the detection percentages, false positives and false negatives for each image and for each simulation code, resulting in the scenarios with the most detection problems and the most accurate algorithm in face detection.

A major challenge for utilities is energy theft, wherein malicious actors steal energy for financial gain. One such form of theft in the smart grid is the fraudulent amplification of energy generation measurements from DERs, such as photo-voltaics. It is important to detect this form of malicious activity, but in a way that ensures the privacy of customers. Not considering privacy aspects could result in a backlash from customers and a heavily curtailed deployment of services, for example. In this short paper, we present a novel privacy-preserving approach to the detection of manipulated DER generation measurements.

With the rapid development of radio detection and wireless communication, narrowband radio-frequency interference (NB-RFI) is a serious threat for GNSS-R (global navigation satellite systems - reflectometry) receivers. However, interferometric GNSS-R (iGNSS-R) is more prone to the NB-RFIs than conventional GNSS-R (cGNSS-R), due to wider bandwidth and unclean replica. Therefore, there is strong demand of detecting and mitigating NB-RFIs for GNSS-R receivers, especially iGNSS-R receivers. Hence, focusing on working with high sampling rate and simplifying the fixed-point implementation on FPGA, this paper proposes a system design exploiting cascading IIR band-stop filters (BSFs) to suppress NB-RFIs. Furthermore, IIR BSF compared with IIR notch filter (NF) and IIR band-pass filter (BPF) is the merely choice that is able to mitigate both white narrowband interference (WNBI) and continuous wave interference (CWI) well. Finally, validation and evaluation are conducted, and then it is indicated that the system design can detect NB-RFIs and suppress WNBI and CWI effectively, which improves the signal-to-noise ratio (SNR) of the Delay-Doppler map (DDM).

Over the last years, the maritime sector has seen an important increase in digital systems on board. Whether used for platform management, navigation, logistics or office tasks, a modern ship can be seen as a fully featured, complex and moving information system. Meanwhile, cyber threats on the sector are real and, for instance, the year 2018 has seen a number of harmful public ransomware attacks impacting shore and ashore assets. Gaining cyber situation recognition, comprehension and projection through Maritime Cyber Situational Awareness is therefore a challenging but essential task for the sector. However, its elaboration has to face a number of issues, such as the collect and fusion of real-time data coming from the ships and an efficient visualization and situation sharing across maritime actors. In this paper, we describe our current work and results for maritime cyber situational awareness elaboration. Even if its development is still going on, the first operational feedback is very encouraging.

Wireless Sensor Network (WSN) faces critical security challenges due to malware(worm, virus, malicious code etc.) attack. When a single node gets compromised by malware then start to spread in entire sensor network through neighboring sensor nodes. To understand the dynamics of malware propagation in WSN proposed a Susceptible-Exposed-Infectious-Recovered-Dead (SEIRD) model. This model used the concept of epidemiology. The model focused on early detection of malicious signals presence in the network and accordingly application of security mechanism for its removal. The early detection method helps in controlling of malware spread and reduce battery consumption of sensor nodes. In this paper study the dynamics of malware propagation and stability analysis of the system. In epidemiology basic reproduction number is a crucial parameter which is used for the determination of malware status in the system. The expression of basic reproduction number has been obtained. Analyze the propagation dynamics and compared with previous model. The proposed model provides improved security mechanism in comparison to previous one. The extensive simulation results conform the analytical investigation and accuracy of proposed model.

Insider threats are one of the most challenging issues in the world of computer networks. Now a day, most of the companies are relying on cloud services to get scalable data services and to reduce cost. The inclusion of cloud environment has spread the canvas for insider threats because cloud service providers are also there in addition to the organization that outsourced for cloud services. In this paper, multiple existing approaches to handle the insider threats in cloud environment have been investigated and analyzed thoroughly. The comparison of these techniques depicts which better approaches in the paradigm of cloud computing exist.

Intrusion detection system is described as a data monitoring, network activity study and data on possible vulnerabilities and attacks in advance. One of the main limitations of the present intrusion detection technology is the need to take out fake alarms so that the user can confound with the data. This paper deals with the different types of IDS their behaviour, response time and other important factors. This paper also demonstrates and brings out the advantages and disadvantages of six latest intrusion detection techniques and gives a clear picture of the recent advancements available in the field of IDS based on the factors detection rate, accuracy, average running time and false alarm rate.

Compressed sensing (CS) integrates sampling and compression into a single step to reduce the processed data amount. However, the CS reconstruction generally suffers from high complexity. To solve this problem, compressive signal processing (CSP) is recently proposed to implement some signal processing tasks directly in the compressive domain without reconstruction. Among various CSP techniques, compressive detection achieves the signal detection based on the CS measurements. This paper investigates the compressive detection problem of random signals when the measurements are corrupted. Different from the current studies that only consider the dense noise, our study considers both the dense noise and sparse error. The theoretical performance is derived, and simulations are provided to verify the derived theoretical results.

A covert channel is a communication channel that is subjugated for illegal flow of information in a way that violates system security policies. It is a dangerous, invisible, undetectable, and developed security attack. Recently, Packet length covert channel has motivated many researchers as it is a one of the most undetectable network covert channels. Packet length covert channel generates a covert traffic that is very similar to normal terrific which complicates the detection of such type of covert channels. This motivates us to introduce a machine learning based detection scheme. Recently, a machine learning approach has proved its capability in many different fields especially in security field as it usually brings up a reliable and realistic results. Based in our developed content and frequency-based features, the developed detection scheme has been fully trained and tested. Our detection scheme has gained an excellent degree of detection accuracy which reaches 98% (zero false negative rate and 0.02 false positive rate).

Modern malware applies a rich arsenal of evasion techniques to render dynamic analysis ineffective. In turn, dynamic analysis tools take great pains to hide themselves from malware; typically this entails trying to be as faithful as possible to the behavior of a real run. We present a novel approach to malware analysis that turns this idea on its head, using an extreme abstraction of the operating system that intentionally strays from real behavior. The key insight is that the presence of malicious behavior is sufficient evidence of malicious intent, even if the path taken is not one that could occur during a real run of the sample. By exploring multiple paths in a system that only approximates the behavior of a real system, we can discover behavior that would often be hard to elicit otherwise. We aggregate features from multiple paths and use a funnel-like configuration of machine learning classifiers to achieve high accuracy without incurring too much of a performance penalty. We describe our system, TAMALES (The Abstract Malware Analysis LEarning System), in detail and present machine learning results using a 330K sample set showing an FPR (False Positive Rate) of 0.10% with a TPR (True Positive Rate) of 99.11%, demonstrating that extreme abstraction can be extraordinarily effective in providing data that allows a classifier to accurately detect malware.

In this paper, we propose a graph-based algorithmic technique for malware detection, utilizing the System-call Dependency Graphs (ScDG) obtained through taint analysis traces. We leverage the grouping of system-calls into system-call groups with respect to their functionality to merge disjoint vertices of ScDG graphs, transforming them to Group Relation Graphs (GrG); note that, the GrG graphs represent malware's behavior being hence more resilient to probable mutations of its structure. More precisely, we extend the use of GrG graphs by mapping their vertices on the plane utilizing the degrees and the vertex-weights of a specific underlying graph of the GrG graph as to compute domination relations. Furthermore, we investigate how the activity of each system-call group could be utilized in order to distinguish graph-representations of malware and benign software. The domination relations among the vertices of GrG graphs result to a new graph representation that we call Coverage Graph of the GrG graph. Finally, we evaluate the potentials of our detection model using graph similarity between Coverage Graphs of known malicious and benign software samples of various types.

With the progress over technology, it is becoming viable to set up mobile ad hoc networks for non-military services as like well. Examples consist of networks of cars, law about communication facilities into faraway areas, and exploiting the solidity between urban areas about present nodes such as cellular telephones according to offload or otherwise keep away from using base stations. In such networks, there is no strong motive according to assume as the nodes cooperate. Some nodes may also be disruptive and partial may additionally attempt according to save sources (e.g. battery power, memory, CPU cycles) through “selfish” behavior. The proposed method focuses on the robustness of packet forwarding: keeping the usual packet throughput over a mobile ad hoc network in the rear regarding nodes that misbehave at the routing layer. Proposed system listen at the routing layer or function no longer try after address attacks at lower layers (eg. jamming the network channel) and passive attacks kind of eavesdropping. Moreover such functionate now not bear together with issues kind of node authentication, securing routes, or message encryption. Proposed solution addresses an orthogonal problem the encouragement concerning proper routing participation.