Biblio

Android gives us opportunity to extract meaningful information from metadata. From the security point of view, the missing important information in metadata of an application could be a sign of suspicious application, which could be directed for extensive analysis. Especially the usage of dangerous permissions is expected to be explained in app descriptions. The permission-to-description fidelity problem in the literature aims to discover such inconsistencies between the usage of permissions and descriptions. This study proposes a new method based on natural language processing and recurrent neural networks. The effect of user reviews on finding such inconsistencies is also investigated in addition to application descriptions. The experimental results show that high precision is obtained by the proposed solution, and the proposed method could be used for triage of Android applications.

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly outperforms state-of-the-art codes designed over several decades of research. The communication channel under consideration is the Gaussian noise channel with feedback, whose study was initiated by Shannon; feedback is known theoretically to improve reliability of communication, but no practical codes that do so have ever been successfully constructed. We break this logjam by integrating information theoretic insights harmoniously with recurrent-neural-network based encoders and decoders to create novel codes that outperform known codes by 3 orders of magnitude in reliability and achieve a 3dB gain in terms of SNR. We also demonstrate several desirable properties of the codes: (a) generalization to larger block lengths, (b) composability with known codes, and (c) adaptation to practical constraints. This result also has broader ramifications for coding theory: even when the channel has a clear mathematical model, deep learning methodologies, when combined with channel-specific information-theoretic insights, can potentially beat state-of-the-art codes constructed over decades of mathematical research.

Advertising channels have evolved from conventional print media, billboards and radio-advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc. While advertisers revisit the design of ad campaigns to concurrently serve the requirements emerging out of new ad channels, it is also critical for advertisers to estimate the contribution from touch-points (view, clicks, converts) on different channels, based on the sequence of customer actions. This process of contribution measurement is often referred to as multi-touch attribution (MTA). In this work, we propose CAMTA, a novel deep recurrent neural network architecture which is a causal attribution mechanism for user-personalised MTA in the context of observational data. CAMTA minimizes the selection bias in channel assignment across time-steps and touchpoints. Furthermore, it utilizes the users' pre-conversion actions in a principled way in order to predict per-channel attribution. To quantitatively benchmark the proposed MTA model, we employ the real-world Criteo dataset and demonstrate the superior performance of CAMTA with respect to prediction accuracy as compared to several baselines. In addition, we provide results for budget allocation and user-behaviour modeling on the predicted channel attribution.

Nowadays, the networks attacks became very sophisticated and hard to be recognized, The traditional types of intrusion detection systems became inefficient in predicting new types of attacks. As the IDS is an important factor in securing the network in the real time, many new effective IDS approaches have been proposed. In this paper, we intend to discuss different Artificial Neural Networks based IDS approaches, also we are going to categorize them in four categories (normal ANN, DNN, CNN, RNN) and make a comparison between them depending on different performance parameters (accuracy, FNR, FPR, training time, epochs and the learning rate) and other factors like the network structure, the classification type, the used dataset. At the end of the survey, we will mention the merits and demerits of each approach and suggest some enhancements to avoid the noticed drawbacks.

Host-based Intrusion Detection Systems HIDS are often based on anomaly detection. Several studies deal with anomaly detection by analyzing the system-call traces and get good detection rates but also a high rate off alse positives. In this paper, we propose a new anomaly detection approach applied on the system-call traces. The normal behavior learning is done using a Sequence to sequence model based on a Variational Encoder-Decoder (VED) architecture that integrates Recurrent Neural Networks (RNN) cells. We exploit the semantics behind the invoking order of system-calls that are then seen as sentences. A preprocessing phase is added to structure and optimize the model input-data representation. After the learning step, a one-class classification is run to categorize the sequences as normal or abnormal. The architecture may be used for predicting abnormal behaviors. The tests are achieved on the ADFA-LD dataset.

Zero-day Web attacks are arguably the most serious threats to Web security, but are very challenging to detect because they are not seen or known previously and thus cannot be detected by widely-deployed signature-based Web Application Firewalls (WAFs). This paper proposes ZeroWall, an unsupervised approach, which works with an existing WAF in pipeline, to effectively detecting zero-day Web attacks. Using historical Web requests allowed by an existing signature-based WAF, a vast majority of which are assumed to be benign, ZeroWall trains a self-translation machine using an encoder-decoder recurrent neural network to capture the syntax and semantic patterns of benign requests. In real-time detection, a zero-day attack request (which the WAF fails to detect), not understood well by self-translation machine, cannot be translated back to its original request by the machine, thus is declared as an attack. In our evaluation using 8 real-world traces of 1.4 billion Web requests, ZeroWall successfully detects real zero-day attacks missed by existing WAFs and achieves high F1-scores over 0.98, which significantly outperforms all baseline approaches.

In recent years, there has been a significant increase in network intrusion attacks which raises a great concern from the privacy and security aspects. Due to the advancement of the technology, cyber-security attacks are becoming very complex such that the current detection systems are not sufficient enough to address this issue. Therefore, an implementation of an intelligent and effective network intrusion detection system would be crucial to solve this problem. In this paper, we use deep learning techniques, namely, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) to design an intelligent detection system which is able to detect different network intrusions. Additionally, we evaluate the performance of the proposed solution using different evaluation matrices and we present a comparison between the results of our proposed solution to find the best model for the network intrusion detection system.

Cross-site scripting (XSS) is one of the main threats of Web applications, which has great harm. How to effectively detect and defend against XSS attacks has become more and more important. Due to the malicious obfuscation of attack codes and the gradual increase in number, the traditional XSS detection methods have some defects such as poor recognition of malicious attack codes, inadequate feature extraction and low efficiency. Therefore, we present a novel approach to detect XSS attacks based on the attention mechanism of Long Short-Term Memory (LSTM) recurrent neural network. First of all, the data need to be preprocessed, we used decoding technology to restore the XSS codes to the unencoded state for improving the readability of the code, then we used word2vec to extract XSS payload features and map them to feature vectors. And then, we improved the LSTM model by adding attention mechanism, the LSTM-Attention detection model was designed to train and test the data. We used the ability of LSTM model to extract context-related features for deep learning, the added attention mechanism made the model extract more effective features. Finally, we used the classifier to classify the abstract features. Experimental results show that the proposed XSS detection model based on LSTM-Attention achieves a precision rate of 99.3% and a recall rate of 98.2% in the actually collected dataset. Compared with traditional machine learning methods and other deep learning methods, this method can more effectively identify XSS attacks.

Style transfer is an emerging trend in the fields of deep learning's applications, especially in images and audio data this is proven very useful and sometimes the results are astonishing. Gradually styles of textual data are also being changed in many novel works. This paper focuses on the transfer of the sentimental vibe of a sentence. Given a positive clause, the negative version of that clause or sentence is generated keeping the context same. The opposite is also done with negative sentences. Previously this was a very tough job because the go-to techniques for such tasks such as Recurrent Neural Networks (RNNs) [1] and Long Short-Term Memories(LSTMs) [2] can't perform well with it. But since newer technologies like Generative Adversarial Network(GAN) and Variational AutoEncoder(VAE) are emerging, this work seem to become more and more possible and effective. In this paper, Multi-Genarative Variational Auto-Encoder is employed to transfer sentiment values. Inspite of working with a small dataset, this model proves to be promising.

Intrusion detection systems (IDS) are important security tools. NIDS monitors network's traffic and HIDS filters local one. HIDS are often based on anomaly detection. Several studies deal with anomaly detection using system-call traces. In this paper, we propose an anomaly detection and prediction approach. System-call traces, invoked by the running programs, are analyzed in real time. For prediction, we use a Sequence to sequence model based on variational encoder-decoder (VED) and variants of Recurrent Neural Networks (RNN), these architectures showed their performance on natural language processing. To make the analogy, we exploit the semantics behind the invoking order of system-calls that are then seen as sentences. A preprocessing phase is added to optimize the prediction model input data representation. A one-class classification is done to categorize the sequences into normal or abnormal. Tests are achieved on the ADFA-LD dataset and showed the advantage of the prediction for the intrusion detection/prediction task.

When we are express our internal status, such as emotions, the human body expression we use follows the compositionality principle. It is a theory in linguistic which proposes that the single components of the bodily presentation as well as the rules used to combine them are the major parts to finish this process. In this paper, such principle is applied to the process of expressing and recognizing emotional states through body expression, in which certain key features can be learned to represent certain primitives of the internal emotional state in the form of basic variables. This is done by a hierarchical recurrent neural learning framework (RNN) because of its nonlinear dynamic bifurcation, so that variables can be learned to represent different hierarchies. In addition, we applied some adaptive learning techniques in machine learning for the requirement of real-time emotion recognition, in which a stable representation can be maintained compared to previous work. The model is examined by comparing the PB values between the training and recognition phases. This hierarchical model shows the rationality of the compositionality hypothesis by the RNN learning and explains how key features can be used and combined in bodily expression to show the emotional state.

Smart grids are vulnerable to cyber-attacks, which can cause significant damage and huge economic losses. Generally, state estimation (SE) is used to observe the operation of the grid. State estimation of the grid is vulnerable to false data injection attack (FDIA), so diagnosing this type of malicious attack has a major impact on ensuring reliable operation of the power system. In this paper, we present an effective FDIA detection method based on residual recurrent neural network (R2N2) prediction model and adaptive judgment threshold. Specifically, considering the data contains both linear and nonlinear components, the R2N2 model divides the prediction process into two parts: the first part uses the linear model to fit the state data; the second part predicts the nonlinearity of the residuals of the linear prediction model. The adaptive judgment threshold is inferred through fitting the Weibull distribution with the sum of squared errors between the predicted values and observed values. The thorough simulation results demonstrate that our scheme performs better than other prediction based FDIA detection schemes.

We investigate a deep learning model for action recognition that simultaneously extracts spatio-temporal information from a raw RGB input data. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by combining multiple timescale recurrent dynamics with a conventional convolutional neural network model. The architecture of the proposed model imposes both spatial and temporal constraints simultaneously on its neural activities. The constraints vary, with multiple scales in different layers. As suggested by the principle of upward and downward causation, it is assumed that the network can develop a functional hierarchy using its constraints during training. To evaluate and observe the characteristics of the proposed model, we use three human action datasets consisting of different primitive actions and different compositionality levels. The performance capabilities of the MSTRNN model on these datasets are compared with those of other representative deep learning models used in the field. The results show that the MSTRNN outperforms baseline models while using fewer parameters. The characteristics of the proposed model are observed by analyzing its internal representation properties. The analysis clarifies how the spatio-temporal constraints of the MSTRNN model aid in how it extracts critical spatio-temporal information relevant to its given tasks.

Although sequence-to-sequence attentional neural machine translation (NMT) has achieved great progress recently, it is confronted with two challenges: learning optimal model parameters for long parallel sentences and well exploiting different scopes of contexts. In this paper, partially inspired by the idea of segmenting a long sentence into short clauses, each of which can be easily translated by NMT, we propose a hierarchy-to-sequence attentional NMT model to handle these two challenges. Our encoder takes the segmented clause sequence as input and explores a hierarchical neural network structure to model words, clauses, and sentences at different levels, particularly with two layers of recurrent neural networks modeling semantic compositionality at the word and clause level. Correspondingly, the decoder sequentially translates segmented clauses and simultaneously applies two types of attention models to capture contexts of interclause and intraclause for translation prediction. In this way, we can not only improve parameter learning, but also well explore different scopes of contexts for translation. Experimental results on Chinese-English and English-German translation demonstrate the superiorities of the proposed model over the conventional NMT model.

Nowadays, biometric data is the most common used data in the field of security. Audio signals are one of these biometric data. Voice signals have used frequently in cases such as identification, banking systems, and forensic cases solution. The aim of this study is to determine the gender of voice signals. In the study, many different methods were used to determine the gender of voice signals. Firstly, Mel Frequency kepstrum coefficients were used to extract the feature from the audio signal. Subsequently, these attributes were classified with support vector machines, k-nearest neighborhood method and artificial neural networks. At the other stage of the study, it is aimed to determine gender from audio signals without using feature extraction method. For this, recurrent neural networks (RNN) was used. The performance analyzes of the methods used were made and the results were given. The best accuracy, precision, recall, f-score in the study has found to be 87.04%, 86.32%, 88.58%, 87.43% using K-Nearest-Neighbor algorithm.

In recent years, unmanned aerial vehicles (UAVs) have become increasingly accessible to the public due to their high availability with affordable prices while being equipped with better technology. However, this raises a great concern from both the cyber and physical security perspectives since UAVs can be utilized for malicious activities in order to exploit vulnerabilities by spying on private properties, critical areas or to carry dangerous objects such as explosives which makes them a great threat to the society. Drone identification is considered the first step in a multi-procedural process in securing physical infrastructure against this threat. In this paper, we present drone detection and identification methods using deep learning techniques such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Convolutional Recurrent Neural Network (CRNN). These algorithms will be utilized to exploit the unique acoustic fingerprints of the flying drones in order to detect and identify them. We propose a comparison between the performance of different neural networks based on our dataset which features audio recorded samples of drone activities. The major contribution of our work is to validate the usage of these methodologies of drone detection and identification in real life scenarios and to provide a robust comparison of the performance between different deep neural network algorithms for this application. In addition, we are releasing the dataset of drone audio clips for the research community for further analysis.

Security Requirements classification is an important area to the Software Engineering community in order to build software that is secure, robust and able to withstand attacks. This classification facilitates proper analysis of security requirements so that adequate security mechanisms are incorporated in the development process. Machine Learning techniques have been used in Security Requirements classification to aid in the process that lead to ensuring that correct security mechanisms are designed corresponding to the Security Requirements classifications made to eliminate the risk of security being incorporated in the late stages of development. However, these Machine Learning techniques have been found to have problems including, handcrafting of features, overfitting and failure to perform well with high dimensional data. In this paper we explore Natural Language Processing and Deep Learning to determine if this can be applied to Security Requirements classification.

This paper presents the effects of problem based learning project on a high-school student in Technology school “Electronic systems” associated with Technical University Sofia. The problem is creating an intrusion detection system for Apache HTTP Server with duration 6 months. The intrusion detection system is based on a recurrent neural network classifier namely long-short term memory units.

Due to the massive amount of the network traffic, attackers have a great chance to cause a huge damage to the network system or its users. Intrusion detection plays an important role in ensuring security for the system by detecting the attacks and the malicious activities. In this paper, we utilize CIDDS dataset and apply a deep learning approach, Long-Short-Term Memory (LSTM), to implement intrusion detection system. This research achieves a reasonable accuracy of 0.85.

In recent years, the spreading of malicious social media messages about financial stocks has threatened the security of financial market. Market Anomaly Attacks is an illegal practice in the stock or commodities markets that induces investors to make purchase or sale decisions based on false information. Identifying these threats from noisy social media datasets remains challenging because of the long time sequence in these social media postings, ambiguous textual context and the difficulties for traditional deep learning approaches to handle both temporal and text dependent data such as financial social media messages. This research developed a temporal recurrent neural network (TRNN) approach to capturing both time and text sequence dependencies for intelligent detection of market anomalies. We tested the approach by using financial social media of U.S. technology companies and their stock returns. Compared with traditional neural network approaches, TRNN was found to more efficiently and effectively classify abnormal returns.

Network attack is a significant security issue for modern society. From small mobile devices to large cloud platforms, almost all computing products, used in our daily life, are networked and potentially under the threat of network intrusion. With the fast-growing network users, network intrusions become more and more frequent, volatile and advanced. Being able to capture intrusions in time for such a large scale network is critical and very challenging. To this end, the machine learning (or AI) based network intrusion detection (NID), due to its intelligent capability, has drawn increasing attention in recent years. Compared to the traditional signature-based approaches, the AI-based solutions are more capable of detecting variants of advanced network attacks. However, the high detection rate achieved by the existing designs is usually accompanied by a high rate of false alarms, which may significantly discount the overall effectiveness of the intrusion detection system. In this paper, we consider the existence of spatial and temporal features in the network traffic data and propose a hierarchical CNN+RNN neural network, LuNet. In LuNet, the convolutional neural network (CNN) and the recurrent neural network (RNN) learn input traffic data in sync with a gradually increasing granularity such that both spatial and temporal features of the data can be effectively extracted. Our experiments on two network traffic datasets show that compared to the state-of-the-art network intrusion detection techniques, LuNet not only offers a high level of detection capability but also has a much low rate of false positive-alarm.

Modern advances in sensor, computing, and communication technologies enable various smart grid applications. The heavy dependence on communication technology has highlighted the vulnerability of the electricity grid to false data injection (FDI) attacks that can bypass bad data detection mechanisms. Existing mitigation in the power system either focus on redundant measurements or protect a set of basic measurements. These methods make specific assumptions about FDI attacks, which are often restrictive and inadequate to deal with modern cyber threats. In the proposed approach, a deep learning based framework is used to detect injected data measurement. Our time-series anomaly detector adopts a Convolutional Neural Network (CNN) and a Long Short Term Memory (LSTM) network. To effectively estimate system variables, our approach observes both data measurements and network level features to jointly learn system states. The proposed system is tested on IEEE 39-bus system. Experimental analysis shows that the deep learning algorithm can identify anomalies which cannot be detected by traditional state estimation bad data detection.

The Internet has gradually penetrated into the national economy, politics, culture, military, education and other fields. Due to its openness, interconnectivity and other characteristics, the Internet is vulnerable to all kinds of malicious attacks. The research uses a honeynet to collect attacker information, and proposes a network penetration recognition technology based on interactive behavior analysis. Using Sebek technology to capture the attacker's keystroke record, time series modeling of the keystroke sequences of the interaction behavior is proposed, using a Recurrent Neural Network. The attack recognition method is constructed by using Long Short-Term Memory that solves the problem of gradient disappearance, gradient explosion and long-term memory shortage in ordinary Recurrent Neural Network. Finally, the experiment verifies that the short-short time memory network has a high accuracy rate for the recognition of penetration attacks.

Recent advances in networking and communication technologies have enabled Internet-of-Things (IoT) devices to communicate more frequently and faster. An IoT device typically transmits data over the Internet which is an insecure channel. Cyber attacks such as denial-of-service (DoS), man-in-middle, and SQL injection are considered as big threats to IoT devices. In this paper, an anomaly-based intrusion detection scheme is proposed that can protect sensitive information and detect novel cyber-attacks. The Artificial Bee Colony (ABC) algorithm is used to train the Random Neural Network (RNN) based system (RNN-ABC). The proposed scheme is trained on NSL-KDD Train+ and tested for unseen data. The experimental results suggest that swarm intelligence and RNN successfully classify novel attacks with an accuracy of 91.65%. Additionally, the performance of the proposed scheme is also compared with a hybrid multilayer perceptron (MLP) based intrusion detection system using sensitivity, mean of mean squared error (MMSE), the standard deviation of MSE (SDMSE), best mean squared error (BMSE) and worst mean squared error (WMSE) parameters. All experimental tests confirm the robustness and high accuracy of the proposed scheme.

Computational Intelligence (CI) algorithms/techniques are packaged in a variety of disparate frameworks/applications that all vary with respect to specific supported functionality and implementation decisions that drastically change performance. Developers looking to employ different CI techniques are faced with a series of trade-offs in selecting the appropriate library/framework. These include resource consumption, features, portability, interface complexity, ease of parallelization, etc. Considerations such as language compatibility and familiarity with a particular library make the choice of libraries even more difficult. The paper introduces MeetCI, an open source software framework for computational intelligence software design automation that facilitates the application design decisions and their software implementation process. MeetCI abstracts away specific framework details of CI techniques designed within a variety of libraries. This allows CI users to benefit from a variety of current frameworks without investigating the nuances of each library/framework. Using an XML file, developed in accordance with the specifications, the user can design a CI application generically, and utilize various CI software without having to redesign their entire technology stack. Switching between libraries in MeetCI is trivial and accessing the right library to satisfy a user's goals can be done easily and effectively. The paper discusses the framework's use in design of various applications. The design process is illustrated with four different examples from expert systems and machine learning domains, including the development of an expert system for security evaluation, two classification problems and a prediction problem with recurrent neural networks.