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.

Automatic extractive text summarization is the process of condensing textual information while preserving the important concepts. The proposed method after performing pre-processing on input Persian news articles generates a feature vector of salient sentences from a combination of statistical, semantic and heuristic methods and that are scored and concatenated accordingly. The scoring of the salient features is based on the article's title, proper nouns, pronouns, sentence length, keywords, topic words, sentence position, English words, and quotations. Experimental results on measurements including recall, F-measure, ROUGE-N are presented and compared to other Persian summarizers and shown to provide higher performance.

How to protect users' private data during network data mining has become a hot issue in the fields of big data and network information security. Most current researches on differential privacy k-means clustering algorithms focus on optimizing the selection of initial centroids. However, the traditional privacy budget allocation has the problem that the random noise becomes too large as the number of iterations increases, which will reduce the performance of data clustering. To solve the problem, we improved the way of privacy budget allocation in differentially private clustering algorithm DPk-means, and proposed APDPk-means, a new differential privacy clustering algorithm based on arithmetic progression privacy budget allocation. APDPk-means decomposes the total privacy budget into a decreasing arithmetic progression, allocating the privacy budgets from large to small in the iterative process, so as to ensure the rapid convergence in early iteration. The experiment results show that compared with the other differentially private k-means algorithms, APDPk-means has better performance in availability and quality of the clustering result under the same level of privacy protection.

Analyzing clustering results may lead to the privacy disclosure issue in big data mining. In this paper, we put forward a differential privacy-based protecting data preprocessing method for distance-based clustering. Firstly, the data distortion technique differential privacy is used to prevent the distances in distance-based clustering from disclosing the relationships. Differential privacy may affect the clustering results while protecting privacy. Then an adaptive privacy budget parameter adjustment mechanism is applied for keeping the balance between the privacy protection and the clustering results. By solving the maximum and minimum problems, the differential privacy budget parameter can be obtained for different clustering algorithms. Finally, we conduct extensive experiments to evaluate the performance of our proposed method. The results demonstrate that our method can provide privacy protection with precise clustering results.

Warnings happen a lot in real transmission networks. These warnings can affect people's lives. It is significant to analyze the alarm association rules in the network. Many algorithms can help solve this problem but not considering the actual physical significance. Therefore, in this study, we mine the association rules in warning weblogs based on a sequential mining algorithm (GSP) with topology structure. We define a topology constraint from network physical connection data. Under the topology constraint, network nodes have topology relation if they are directly connected or have a common adjacency node. In addition, due to the large amount of data, we implement the hash-tree search method to improve the mining efficiency. The theoretical solution is feasible and the simulation results verify our method. In simulation, the topology constraint improves the accuracy for 86%-96% and decreases the run time greatly at the same time. The hash-tree based mining results show that hash tree efficiency improvements are in 3-30% while the number of patterns remains unchanged. In conclusion, using our method can mine association rules efficiently and accurately in warning weblogs.

In recent years, sentiment analysis has been aware within software engineering domain. While automated sentiment analysis has long been suffering from doubt of accuracy, the tool performance is unstable when being applied on datasets other than the original dataset for evaluation. Researchers also have the disagreements upon if machine learning algorithms perform better than conventional lexicon and rule based approaches. In this paper, we looked into the factors in datasets that may affect the evaluation performance, also evaluated the popular machine learning algorithms in sentiment analysis, then proposed a novel structure for automated sentiment tool combines advantages from both approaches.

Software security is a major concern of the developers who intend to deliver a reliable software. Although there is research that focuses on vulnerability prediction and discovery, there is still a need for building security-specific metrics to measure software security and vulnerability-proneness quantitatively. The existing methods are either based on software metrics (defined on the physical characteristics of code; e.g. complexity or lines of code) which are not security-specific or some generic patterns known as nano-patterns (Java method-level traceable patterns that characterize a Java method or function). Other methods predict vulnerabilities using text mining approaches or graph algorithms which perform poorly in cross-project validation and fail to be a generalized prediction model for any system. In this paper, we envision to construct an automated framework that will assist developers to assess the security level of their code and guide them towards developing secure code. To accomplish this goal, we aim to refine and redefine the existing nano-patterns and software metrics to make them more security-centric so that they can be used for measuring the software security level of a source code (either file or function) with higher accuracy. In this paper, we present our visionary approach through a series of three consecutive studies where we (1) will study the challenges of the current software metrics and nano-patterns in vulnerability prediction, (2) will redefine and characterize the nano-patterns and software metrics so that they can capture security-specific properties of code and measure the security level quantitatively, and finally (3) will implement an automated framework for the developers to automatically extract the values of all the patterns and metrics for the given code segment and then flag the estimated security level as a feedback based on our research results. We accomplished some preliminary experiments and presented the results which indicate that our vision can be practically implemented and will have valuable implications in the community of software security.

Mobile phones have become nowadays a commodity to the majority of people. Using them, people are able to access the world of Internet and connect with their friends, their colleagues at work or even unknown people with common interests. This proliferation of the mobile devices has also been seen as an opportunity for the cyber criminals to deceive smartphone users and steel their money directly or indirectly, respectively, by accessing their bank accounts through the smartphones or by blackmailing them or selling their private data such as photos, credit card data, etc. to third parties. This is usually achieved by installing malware to smartphones masking their malevolent payload as a legitimate application and advertise it to the users with the hope that mobile users will install it in their devices. Thus, any existing application can easily be modified by integrating a malware and then presented it as a legitimate one. In response to this, scientists have proposed a number of malware detection and classification methods using a variety of techniques. Even though, several of them achieve relatively high precision in malware classification, there is still space for improvement. In this paper, we propose a text mining all repeated pattern detection method which uses the decompiled files of an application in order to classify a suspicious application into one of the known malware families. Based on the experimental results using a real malware dataset, the methodology tries to correctly classify (without any misclassification) all randomly selected malware applications of 3 categories with 3 different families each.

The use of the Internet of Things (IoT) devices has surged in recent years. However, due to the lack of substantial security, IoT devices are vulnerable to cyber-attacks like Denial-of-Service (DoS) attacks. Most of the current security solutions are either computationally expensive or unscalable as they require known attack signatures or full packet inspection. In this paper, we introduce a novel Graph-based Outlier Detection in Internet of Things (GODIT) approach that (i) represents smart home IoT traffic as a real-time graph stream, (ii) efficiently processes graph data, and (iii) detects DoS attack in real-time. The experimental results on real-world data collected from IoT-equipped smart home show that GODIT is more effective than the traditional machine learning approaches, and is able to outperform current graph-stream anomaly detection approaches.

Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

Innovation and creativity have played an important role in the development of every field of life, relatively less but it has created several problems too. Intrusion detection is one of those problems which became difficult with the advancement in computer networks, multiple researchers with multiple techniques have come forward to solve this crucial issue, but network security is still a challenge. In our research, we have come across an idea to detect intrusion using a deep learning algorithm in combination with statistical data analysis of KDD cup 99 datasets. Firstly, we have applied statistical analysis on the given data set to generate a simplified form of data, so that a less complex binary classification model of artificial neural network could apply for data classification. Our system has decreased the complexity of the system and has improved the response time.

Continuous growth in sensor data and other temporal sequence data necessitates efficient retrieval and similarity search support on these big time series datasets. However, finding exact similarity results, especially at the granularity of subsequences, is known to be prohibitively costly for large data sets. In this paper, we thus propose an efficient framework for solving this exact subsequence similarity match problem, called TINN (TIme series Nearest Neighbor search). Exploiting the range interval diversity properties of time series datasets, TINN captures similarity at two levels of abstraction, namely, relationships among subsequences within each long time series and relationships across distinct time series in the data set. These relationships are compactly organized in an augmented relationship graph model, with the former relationships encoded in similarity vectors at TINN nodes and the later captured by augmented edge types in the TINN Graph. Query processing strategy deploy novel pruning techniques on the TINN Graph, including node skipping, vertical and horizontal pruning, to significantly reduce the number of time series as well as subsequences to be explored. Comprehensive experiments on synthetic and real world time series data demonstrate that our TINN model consistently outperforms state-of-the-art approaches while still guaranteeing to retrieve exact matches.

With the introduction of computer methods, the amount of material and processing accuracy of policy text analysis have been greatly improved. In this paper, Text mining(TM) and latent semantic analysis(LSA) were used to collect policy documents and extract policy elements from them. Fuzzy association rule mining(FARM) technique and partial association test (PA) were used to discover the causal relationships and impact degrees between elements, and a fuzzy cognitive map (FCM) was developed to deduct the evolution of elements through a soft computing method. This non-interventionist approach avoids the validity defects caused by the subjective bias of researchers and provides policy makers with more objective policy suggestions from a neutral perspective. To illustrate the accuracy of this method, this study experimented by taking the state-owned capital layout adjustment related policies as an example, and proved that this method can effectively analyze policy text.

Inference of unknown opinions with uncertain, adversarial (e.g., incorrect or conflicting) evidence in large datasets is not a trivial task. Without proper handling, it can easily mislead decision making in data mining tasks. In this work, we propose a highly scalable opinion inference probabilistic model, namely Adversarial Collective Opinion Inference (Adv-COI), which provides a solution to infer unknown opinions with high scalability and robustness under the presence of uncertain, adversarial evidence by enhancing Collective Subjective Logic (CSL) which is developed by combining SL and Probabilistic Soft Logic (PSL). The key idea behind the Adv-COI is to learn a model of robust ways against uncertain, adversarial evidence which is formulated as a min-max problem. We validate the out-performance of the Adv-COI compared to baseline models and its competitive counterparts under possible adversarial attacks on the logic-rule based structured data and white and black box adversarial attacks under both clean and perturbed semi-synthetic and real-world datasets in three real world applications. The results show that the Adv-COI generates the lowest mean absolute error in the expected truth probability while producing the lowest running time among all.

Finite-state machine (FSM) is widely used as control unit in most digital designs. Many intellectual property protection and obfuscation techniques leverage on the exponential number of possible states and state transitions of large FSM to secure a physical design with the reason that it is challenging to retrieve the FSM design from its downstream design or physical implementation without knowledge of the design. In this paper, we postulate that this assumption may not be sustainable with big data analytics. We demonstrate by applying a data mining technique to analyze sufficiently large amount of data collected from a full scan design to identify its FSM state registers. An impact metric is introduced to discriminate FSM state registers from other registers. A decision tree algorithm is constructed from the scan data for the regression analysis of the dependency of other registers on a chosen register to deduce its impact. The registers with the greater impact are more likely to be the FSM state registers. The proposed scheme is applied on several complex designs from OpenCores. The experiment results show the feasibility of our scheme in correctly identifying most FSM state registers with a high hit rate for a large majority of the designs.

Bitcoin [1] as a popular digital currency has been a target of theft and other illegal activities. Key to the forensic investigation is to identify bitcoin addresses involved in bitcoin transfers. This paper presents a framework, FABT, for forensic analysis of bitcoin transactions by identifying suspicious bitcoin addresses. It formalizes the clues of a given case as transaction patterns defined over a comprehensive set of features. FABT converts the bitcoin transaction data into a formal model, called Bitcoin Transaction Net (BTN). The traverse of all bitcoin transactions in the order of their occurrences is captured by the firing sequence of all transitions in the BTN. We have applied FABT to identify suspicious addresses in the Mt.Gox case. A subgroup of the suspicious addresses has been found to share many characteristics about the received/transferred amount, number of transactions, and time intervals.

Detecting repackaged apps is one of the important issues in the Android ecosystem. Many attackers usually reverse engineer a legitimate app, modify or embed malicious codes into the app, repackage and distribute it in the online markets. They also employ code obfuscation techniques to hide app cloning or repackaging. In this paper, we propose a new technique for detecting repackaged Android apps, which is robust to code obfuscation. The technique analyzes the similarity of Android apps based on the method call information of component classes that receive implicit intents. We developed a tool Calldroid that implemented the proposed technique, and evaluated it on apps transformed using well-known obfuscators. The evaluation results showed that the proposed technique can effectively detect repackaged apps.

In the last few years, cryptocurrency mining has become more and more important on the Internet activity and nowadays is even having a noticeable impact on the global economy. This has motivated the emergence of a new malicious activity called cryptojacking, which consists of compromising other machines connected to the Internet and leverage their resources to mine cryptocurrencies. In this context, it is of particular interest for network administrators to detect possible cryptocurrency miners using network resources without permission. Currently, it is possible to detect them using IP address lists from known mining pools, processing information from DNS traffic, or directly performing Deep Packet Inspection (DPI) over all the traffic. However, all these methods are still ineffective to detect miners using unknown mining servers or result too expensive to be deployed in real-world networks with large traffic volume. In this paper, we present a machine learning-based method able to detect cryptocurrency miners using NetFlow/IPFIX network measurements. Our method does not require to inspect the packets' payload; as a result, it achieves cost-efficient miner detection with similar accuracy than DPI-based techniques.

The anonymity and decentralization of Bitcoin make it widely accepted in illegal transactions, such as money laundering, drug and weapon trafficking, gambling, to name a few, which has already caused significant security risk all around the world. The obvious de-anonymity approach that matches transaction addresses and users is not possible in practice due to limited annotated data set. In this paper, we divide addresses into four types, exchange, gambling, service, and general, and propose targeted addresses identification algorithms with high fault tolerance which may be employed in a wide range of applications. We use network representation learning to extract features and train imbalanced multi-classifiers. Experimental results validated the effectiveness of the proposed method.

Recent research has shown that machine learning models are susceptible to adversarial examples, allowing attackers to trick a machine learning model into making a mistake and producing an incorrect output. Adversarial examples are commonly constructed or discovered by using gradient-based methods that require white-box access to the model. In most real-world AI system deployments, having complete access to the machine learning model is an unrealistic threat model. However, it is possible for an attacker to construct adversarial examples even in the black-box case - where we assume solely a query capability to the model - with a variety of approaches each with its advantages and shortcomings. We introduce AutoAttacker, a novel reinforcement learning framework where agents learn how to operate around the black-box model by querying it, to effectively extract the underlying decision behaviour, and to undermine it successfully. AutoAttacker is a first of kind framework that uses reinforcement learning and assumes nothing about the differentiability or structure of the underlying function and is thus robust towards common defenses like gradient obfuscation or adversarial training. Finally, without differentiable output, as in binary classification, most methods cease to operate and require either an approximation of the gradient, or another approach altogether. Our approach, however, maintains the capability to function when the output descriptiveness diminishes.

The purpose of Complex Networks Monitoring and Security and Fraud Detection for Enterprises - CoNeSec track is two-fold: Firstly, the track offers a forum for scientists and engineers to exchange ideas on novel analytical techniques using network log data. Secondly, the track has a thematic focus on emerging technology for complex network, security and privacy. We seek publications on all theoretical and practical work in areas related to the theme above.

Wearable technology has been on an exponential rise and shows no signs of slowing down. One category of wearable technology is Fitness bands, which have the potential to show a user's activity levels and location data. Such information stored in fitness bands is just the beginning of a long trail of evidence fitness bands can store, which represents a huge opportunity to digital forensic practitioners. On the surface of recent work and research in this area, there does not appear to be any similar work that has already taken place on fitness bands and particularly, the devices in this study, a Garmin Forerunner 110, a Fitbit Charge HR and a Generic low-cost HETP fitness tracker. In this paper, we present our analysis of these devices for any possible digital evidence in a forensically sound manner, identifying files of interest and location data on the device. Data accuracy and validity of the evidence is shown, as a test run scenario wearing all of the devices allowed for data comparison analysis.

In Bitcoin's incentive system that supports open mining pools, block withholding attacks incur huge security threats. In this paper, we investigate the mutual attacks among pools as this determines the macroscopic utility of the whole distributed system. Existing studies on pools' interactive attacks usually employ the conventional game theory, where the strategies of the players are considered pure and equal, neglecting the existence of powerful strategies and the corresponding favorable game results. In this study, we take advantage of the Zero-Determinant (ZD) strategy to analyze the block withholding attack between any two pools, where the ZD adopter has the unilateral control on the expected payoffs of its opponent and itself. In this case, we are faced with the following questions: who can adopt the ZD strategy? individually or simultaneously? what can the ZD player achieve? In order to answer these questions, we derive the conditions under which two pools can individually or simultaneously employ the ZD strategy and demonstrate the effectiveness. To the best of our knowledge, we are the first to use the ZD strategy to analyze the block withholding attack among pools.

Cyber breaches can result in disruption to business operations, reputation damage as well as directly affecting the financial stability of the targeted corporations, with potential impacts on future profits and stock values. Automatic network-stream monitoring becomes necessary for cyber situation awareness, and time-series anomaly detection plays an important role in network stream monitoring. This study surveyed recent research on time-series analysis methods in respect of parametric and non-parametric techniques, and popular machine learning platforms for data analysis on streaming data on both single server and cloud computing environments. We believe it provides a good reference for researchers in both academia and industry to select suitable (time series) data analysis techniques, and computing platforms, dependent on the data scale and real-time requirements.

Event logs that originate from information systems enable comprehensive analysis of business processes, e.g., by process model discovery. However, logs potentially contain sensitive information about individual employees involved in process execution that are only partially hidden by an obfuscation of the event data. In this paper, we therefore address the risk of privacy-disclosure attacks on event logs with pseudonymized employee information. To this end, we introduce PRETSA, a novel algorithm for event log sanitization that provides privacy guarantees in terms of k-anonymity and t-closeness. It thereby avoids disclosure of employee identities, their membership in the event log, and their characterization based on sensitive attributes, such as performance information. Through step-wise transformations of a prefix-tree representation of an event log, we maintain its high utility for discovery of a performance-annotated process model. Experiments with real-world data demonstrate that sanitization with PRETSA yields event logs of higher utility compared to methods that exploit frequency-based filtering, while providing the same privacy guarantees.