Biblio

Current procedures for anomaly detection in self-organizing mobile communication networks use network-centric approaches to identify dysfunctional serving nodes. In this paper, a user-centric approach and a novel methodology for anomaly detection is proposed, where the Quality of Experience (QoE) metric is used to evaluate the end-user experience. The system model demonstrates how dysfunctional serving eNodeBs are successfully detected by implementing a parametric QoE model using machine learning for prediction of user QoE in a network scenario created by the ns-3 network simulator. This approach can play a vital role in the future ultra-dense and green mobile communication networks that are expected to be both self- organizing and self-healing.

In recent years, there is a surge of interest in approaches pertaining to security issues of Internet of Things deployments and applications that leverage machine learning and deep learning techniques. A key prerequisite for enabling such approaches is the development of scalable infrastructures for collecting and processing security-related datasets from IoT systems and devices. This paper introduces such a scalable and configurable data collection infrastructure for data-driven IoT security. It emphasizes the collection of (security) data from different elements of IoT systems, including individual devices and smart objects, edge nodes, IoT platforms, and entire clouds. The scalability of the introduced infrastructure stems from the integration of state of the art technologies for large scale data collection, streaming and storage, while its configurability relies on an extensible approach to modelling security data from a variety of IoT systems and devices. The approach enables the instantiation and deployment of security data collection systems over complex IoT deployments, which is a foundation for applying effective security analytics algorithms towards identifying threats, vulnerabilities and related attack patterns.

So-called IoT, based on use of enabling technologies like 5G, Wi-Fi, BT, NFC, RFID, IPv6 as well as being widely applied for sensor networks, robots, Wearable and Cyber-PHY, invades rapidly to our every day. There are a lot of apps and software platforms to IoT support. However, a most important problem of QoS optimization, which lays in Performance, Reliability and Scalability for IoT, is not yet solved. The extended Internet of the future needs these solutions based on the cooperation between fog and clouds with delegating of the analytics blocks via agents, adaptive interfaces and protocols. The next problem is as follows: IoT can generate large arrays of unmanaged, weakly-structured, and non-configured data of various types, known as "Big Data". The given papers deals with the both problems. A special problem is Security and Privacy in potentially "dangerous" IoTscenarios. Anyway, this subject needs as special discussion for risks evaluation and cooperative intrusion detection. Some advanced approaches for optimization of Performance, Reliability and Scalability for IoT-solutions are offered within the paper. The paper discusses the Best Practises and Case Studies aimed to solution of the established problems.

Wearables are now ubiquitous items equipped with a multitude of sensors such as GPS, accelerometer, or Bluetooth. The raw data from this sensors are typically used in a health context. However, we can also use it for security purposes. In this paper, we present a solution that aims at using data from the sensors of a wearable device to identify the password a user is typing on a keyboard by using machine learning algorithms. Hence, the purpose is to determine whether a malicious third party application could extract sensitive data through the raw data that it has access to.

Security patches in open source software (OSS) not only provide security fixes to identified vulnerabilities, but also make the vulnerable code public to the attackers. Therefore, armored attackers may misuse this information to launch N-day attacks on unpatched OSS versions. The best practice for preventing this type of N-day attacks is to keep upgrading the software to the latest version in no time. However, due to the concerns on reputation and easy software development management, software vendors may choose to secretly patch their vulnerabilities in a new version without reporting them to CVE or even providing any explicit description in their change logs. When those secretly patched vulnerabilities are being identified by armored attackers, they can be turned into powerful "0-day" attacks, which can be exploited to compromise not only unpatched version of the same software, but also similar types of OSS (e.g., SSL libraries) that may contain the same vulnerability due to code clone or similar design/implementation logic. Therefore, it is critical to identify secret security patches and downgrade the risk of those "0-day" attacks to at least "n-day" attacks. In this paper, we develop a defense system and implement a toolset to automatically identify secret security patches in open source software. To distinguish security patches from other patches, we first build a security patch database that contains more than 4700 security patches mapping to the records in CVE list. Next, we identify a set of features to help distinguish security patches from non-security ones using machine learning approaches. Finally, we use code clone identification mechanisms to discover similar patches or vulnerabilities in similar types of OSS. The experimental results show our approach can achieve good detection performance. A case study on OpenSSL, LibreSSL, and BoringSSL discovers 12 secret security patches.

In this paper we propose a two-level hybrid anomalous activity detection model for intrusion detection in IoT networks. The level-1 model uses flow-based anomaly detection, which is capable of classifying the network traffic as normal or anomalous. The flow-based features are extracted from the CICIDS2017 and UNSW-15 datasets. If an anomaly activity is detected then the flow is forwarded to the level-2 model to find the category of the anomaly by deeply examining the contents of the packet. The level-2 model uses Recursive Feature Elimination (RFE) to select significant features and Synthetic Minority Over-Sampling Technique (SMOTE) for oversampling and Edited Nearest Neighbors (ENN) for cleaning the CICIDS2017 and UNSW-15 datasets. Our proposed model precision, recall and F score for level-1 were measured 100% for the CICIDS2017 dataset and 99% for the UNSW-15 dataset, while the level-2 model precision, recall, and F score were measured at 100 % for the CICIDS2017 dataset and 97 % for the UNSW-15 dataset. The predictor we introduce in this paper provides a solid framework for the development of malicious activity detection in IoT networks.

Android operating systems have become a prime target for cyber attackers due to security vulnerabilities in the underlying operating system and application design. Recently, anomaly detection techniques are widely studied for security vulnerabilities detection and classification. However, the ability of the attackers to create new variants of existing malware using various masking techniques makes it harder to deploy these techniques effectively. In this research, we present a robust and effective vulnerabilities detection approach based on anomaly detection in a system calls of benign and malicious Android application. The anomaly in our study is type, frequency, and sequence of system calls that represent a vulnerability. Our system monitors the processes of benign and malicious application and detects security vulnerabilities based on the combination of parameters and metrics, i.e., type, frequency and sequence of system calls to classify the process behavior as benign or malign. The detection algorithm detects the anomaly based on the defined scoring function f and threshold ρ. The system refines the detection process by applying machine learning techniques to find a combination of system call metrics and explore the relationship between security bugs and the pattern of system calls detected. The experiment results show the detection rate of the proposed algorithm based on precision, recall, and f-score for different machine learning algorithms.

Containers have become increasingly popular for deploying applications in cloud computing infrastructures. However, recent studies have shown that containers are prone to various security attacks. In this paper, we conduct a study on the effectiveness of various vulnerability detection schemes for containers. Specifically, we implement and evaluate a set of static and dynamic vulnerability attack detection schemes using 28 real world vulnerability exploits that widely exist in docker images. Our results show that the static vulnerability scanning scheme only detects 3 out of 28 tested vulnerabilities and dynamic anomaly detection schemes detect 22 vulnerability exploits. Combining static and dynamic schemes can further improve the detection rate to 86% (i.e., 24 out of 28 exploits). We also observe that the dynamic anomaly detection scheme can achieve more than 20 seconds lead time (i.e., a time window before attacks succeed) for a group of commonly seen attacks in containers that try to gain a shell and execute arbitrary code.

As the next generation of the power system, smart grid develops towards automated and intellectualized. Along with the benefits brought by smart grids, e.g., improved energy conversion rate, power utilization rate, and power supply quality, are the security challenges. One of the most important issues in smart grids is to ensure reliable communication between the secondary equipment. The state-of-art method to ensure smart grid security is to detect cyber attacks by deep learning. However, due to the small number of negative samples, the performance of the detection system is limited. In this paper, we propose a novel approach that utilizes the Generative Adversarial Network (GAN) to generate abundant negative samples, which helps to improve the performance of the state-of-art detection system. The evaluation results demonstrate that the proposed method can effectively improve the performance of the detection system by 4%.

The technological development of the energy sector also produced complex data. In this study, the relationship between smart grid and big data approaches have been investigated. After analyzing which areas of the smart grid system use big data technologies and technologies, big data technologies for detecting smart grid attacks have received attention. Big data analytics can produce efficient solutions and it is especially important to choose which algorithms and metrics to use. For this reason, an application prototype has been proposed that uses a big data method to detect attacks on the smart grid. The algorithm with high accuracy was determined to be 92% for random forests and 87% for decision trees.

From financial services platforms to social networks to vehicle control, software has come to mediate many activities of daily life. Governing bodies and standards organizations have responded to this trend by creating regulations and standards to address issues such as safety, security and privacy. In this environment, the compliance of software development to standards and regulations has emerged as a key requirement. Compliance claims and arguments are often captured in assurance cases, with linked evidence of compliance. Evidence can come from testcases, verification proofs, human judgement, or a combination of these. That is, we try to build (safety-critical) systems carefully according to well justified methods and articulate these justifications in an assurance case that is ultimately judged by a human. Yet software is deeply rooted in uncertainty making pragmatic assurance more inductive than deductive: most of complex open-world functionality is either not completely specifiable (due to uncertainty) or it is not cost-effective to do so, and deductive verification cannot happen without specification. Inductive assurance, achieved by sampling or testing, is easier but generalization from finite set of examples cannot be formally justified. And of course the recent popularity of constructing software via machine learning only worsens the problem - rather than being specified by predefined requirements, machine-learned components learn existing patterns from the available training data, and make predictions for unseen data when deployed. On the surface, this ability is extremely useful for hard-to specify concepts, e.g., the definition of a pedestrian in a pedestrian detection component of a vehicle. On the other, safety assessment and assurance of such components becomes very challenging. In this talk, I focus on two specific approaches to arguing about safety and security of software under uncertainty. The first one is a framework for managing uncertainty in assurance cases (for "conventional" and "machine-learned" systems) by systematically identifying, assessing and addressing it. The second is recent work on supporting development of requirements for machine-learned components in safety-critical domains.

With the application of integrated circuits (ICs) appears in all aspects of life, whether an IC is security and reliable has caused increasing worry which is of significant necessity. An attacker can achieve the malicious purpose by adding or removing some modules, so called hardware Trojans (HTs). In this paper, we use side-channel analysis (SCA) and support vector machine (SVM) classifier to determine whether there is a Trojan in the circuit. We use SAKURA-G circuit board with Xilinx SPARTAN-6 to complete our experiment. Results show that the Trojan detection rate is up to 93% and the classification accuracy is up to 91.8475%.

In recent years, various cloud-based services have been introduced in our daily lives, and information security is now an important topic for protecting the users. In the literature, many technologies have been proposed and incorporated into different services. Data hiding or steganography is a data protection technology, and images are often used as the cover data. On the other hand, steganalysis is an important tool to test the security strength of a steganography technique. So far, steganalysis has been used mainly for detecting the existence of secret data given an image, i.e., to classify if the given image is a normal or a stego image. In this paper, we investigate the possibility of identifying the locations of the embedded data if the a given image is suspected to be a stego image. The purpose is of two folds. First, we would like to confirm the decision made by the first level steganalysis; and the second is to provide a way to guess the size of the embedded data. Our experimental results show that in most cases the embedding positions can be detected. This result can be useful for developing more secure steganography technologies.

With the rapid growth in online services, hacking (alternatively attacking) on online database applications has become a grave concern now. Attacks on online database application are being frequently reported. Among these attacks, the SQL injection attack is at the top of the list. The hackers alter the SQL query sent by the user and inject malicious code therein. Hence, they access the database and manipulate the data. It is reported in the literature that the traditional SQL injection detection algorithms fail to prevent this type of attack. In this paper, we propose a machine learning based heuristic algorithm to prevent the SQL injection attack. We use a dataset of 616 SQL statements to train and test 23 different machine learning classifiers. Among these classifiers, we select the best five classifiers based on their detection accuracy and develop a Graphical User Interface (GUI) application based on these five classifiers. We test our proposed algorithm and the results show that our algorithm is able to detect the SQL injection attack with a high accuracy (93.8%).

SQL injection attacks are a kind of the greatest security risks on Web applications. Much research has been done to detect SQL injection attacks by rule matching and syntax tree. However, due to the complexity and variety of SQL injection vulnerabilities, these approaches fail to detect unknown and variable SQL injection attacks. In this paper, we propose a model, ATTAR, to detect SQL injection attacks using grammar pattern recognition and access behavior mining. The most important idea of our model is to extract and analyze features of SQL injection attacks in Web access logs. To achieve this goal, we first extract and customize Web access log fields from Web applications. Then we design a grammar pattern recognizer and an access behavior miner to obtain the grammatical and behavioral features of SQL injection attacks, respectively. Finally, based on two feature sets, machine learning algorithms, e.g., Naive Bayesian, SVM, ID3, Random Forest, and K-means, are used to train and detect our model. We evaluated our model on these two feature sets, and the results show that the proposed model can effectively detect SQL injection attacks with lower false negative rate and false positive rate. In addition, comparing the accuracy of our model based on different algorithms, ID3 and Random Forest have a better ability to detect various kinds of SQL injection attacks.

The early discovery of security bugs in JavaScript (JS) engines is crucial for protecting Internet users from adversaries abusing zero-day vulnerabilities. Browser vendors, bug bounty hunters, and security researchers have been eager to find such security bugs by leveraging state-of-the-art fuzzers as well as their domain expertise. They report a bug when observing a crash after executing their JS test since a crash is an early indicator of a potential bug. However, it is difficult to identify whether such a crash indeed invokes security bugs in JS engines. Thus, unskilled bug reporters are unable to assess the security severity of their new bugs with JS engine crashes. Today, this classification of a reported security bug is completely manual, depending on the verdicts from JS engine vendors. We investigated the feasibility of applying various machine learning classifiers to determine whether an observed crash triggers a security bug. We designed and implemented CRScope, which classifies security and non-security bugs from given crash-dump files. Our experimental results on 766 crash instances demonstrate that CRScope achieved 0.85, 0.89, and 0.93 Area Under Curve (AUC) for Chakra, V8, and SpiderMonkey crashes, respectively. CRScope also achieved 0.84, 0.89, and 0.95 precision for Chakra, V8, and SpiderMonkey crashes, respectively. This outperforms the previous study and existing tools including Exploitable and AddressSanitizer. CRScope is capable of learning domain-specific expertise from the past verdicts on reported bugs and automatically classifying JS engine security bugs, which helps improve the scalable classification of security bugs.

With the spread of wireless application, huge amount of data is generated every day. Thanks to its elasticity, machine learning is becoming a fundamental brick in this field, and many of applications are developed with the use of it and the several techniques that it offers. However, machine learning suffers on different problems and people that use it often are not aware of the possible threats. Often, an adversary tries to exploit these vulnerabilities in order to obtain benefits; because of this, adversarial machine learning is becoming wide studied in the scientific community. In this paper, we show state-of-the-art adversarial techniques and possible countermeasures, with the aim of warning people regarding sensible argument related to the machine learning.

Machine learning systems have had enormous success in a wide range of fields from computer vision, natural language processing, and anomaly detection. However, such systems are vulnerable to attackers who can cause deliberate misclassification by introducing small perturbations. With machine learning systems being proposed for cyber attack detection such attackers are cause for serious concern. Despite this the vast majority of adversarial machine learning security research is focused on the image domain. This work gives a brief overview of adversarial machine learning and machine learning used in cyber attack detection and suggests key differences between the traditional image domain of adversarial machine learning and the cyber domain. Finally we show an adversarial machine learning attack on an industrial control system.

Collaboration between humans and machines does not necessarily lead to better outcomes.

In recent years, cyber attack techniques are increasingly sophisticated, and blocking the attack is more and more difficult, even if a kind of counter measure or another is taken. In order for a successful handling of this situation, it is crucial to have a prediction of cyber attacks, appropriate precautions, and effective utilization of cyber intelligence that enables these actions. Malicious hackers share various kinds of information through particular communities such as the dark web, indicating that a great deal of intelligence exists in cyberspace. This paper focuses on forums on the dark web and proposes an approach to extract forums which include important information or intelligence from huge amounts of forums and identify traits of each forum using methodologies such as machine learning, natural language processing and so on. This approach will allow us to grasp the emerging threats in cyberspace and take appropriate measures against malicious activities.

This study has built a simulation of a smart home system by the Alibaba ECS. The architecture of hardware was based on edge computing technology. The whole method would design a clear classifier to find the boundary between regular and mutation codes. It could be applied in the detection of the mutation code of network. The project has used the dataset vector to divide them into positive and negative type, and the final result has shown the RBF-function SVM method perform best in this mission. This research has got a good network security detection in the IoT systems and increased the applications of machine learning.

Machine learning has been adopted widely to perform prediction and classification. Implementing machine learning increases security risks when computation process involves sensitive data on training and testing computations. We present a proposed system to protect machine learning engines in IoT environment without modifying internal machine learning architecture. Our proposed system is designed for passwordless and eliminated the third-party in executing machine learning transactions. To evaluate our a proposed system, we conduct experimental with machine learning transactions on IoT board and measure computation time each transaction. The experimental results show that our proposed system can address security issues on machine learning computation with low time consumption.

In the modern day and age, credential based authentication systems no longer provide the level of security that many organisations and their services require. The level of trust in passwords has plummeted in recent years, with waves of cyber attacks predicated on compromised and stolen credentials. This method of authentication is also heavily reliant on the individual user's choice of password. There is the potential to build levels of security on top of credential based authentication systems, using a risk based approach, which preserves the seamless authentication experience for the end user. One method of adding this security to a risk based authentication framework, is keystroke dynamics. Monitoring the behaviour of the users and how they type, produces a type of digital signature which is unique to that individual. Learning this behaviour allows dynamic flags to be applied to anomalous typing patterns that are produced by attackers using stolen credentials, as a potential risk of fraud. Methods from statistics and machine learning have been explored to try and implement such solutions. This paper will look at an Autoencoder model for learning the keystroke dynamics of specific users. The results from this paper show an improvement over the traditional tried and tested statistical approaches with an Equal Error Rate of 6.51%, with the additional benefits of relatively low training times and less reliance on feature engineering.

Recent work proposed the concept of backdoor attacks on deep neural networks (DNNs), where misclassification rules are hidden inside normal models, only to be triggered by very specific inputs. However, these "traditional" backdoors assume a context where users train their own models from scratch, which rarely occurs in practice. Instead, users typically customize "Teacher" models already pretrained by providers like Google, through a process called transfer learning. This customization process introduces significant changes to models and disrupts hidden backdoors, greatly reducing the actual impact of backdoors in practice. In this paper, we describe latent backdoors, a more powerful and stealthy variant of backdoor attacks that functions under transfer learning. Latent backdoors are incomplete backdoors embedded into a "Teacher" model, and automatically inherited by multiple "Student" models through transfer learning. If any Student models include the label targeted by the backdoor, then its customization process completes the backdoor and makes it active. We show that latent backdoors can be quite effective in a variety of application contexts, and validate its practicality through real-world attacks against traffic sign recognition, iris identification of volunteers, and facial recognition of public figures (politicians). Finally, we evaluate 4 potential defenses, and find that only one is effective in disrupting latent backdoors, but might incur a cost in classification accuracy as tradeoff.

In this paper, we explore the authorship attribution of The Golden Lotus using the traditional machine learning method of text classification. There are four candidate authors: Shizhen Wang, Wei Xu, Kaixian Li and Zhideng Wang. We choose The Golden Lotus's poems and four candidate authors' poems as data set. According to the characteristics of Chinese ancient poem, we choose Chinese character, rhyme, genre and overlapped word as features. We use six supervised machine learning algorithms, including Logistic Regression, Random Forests, Decision Tree and Naive Bayes, SVM and KNN classifiers respectively for text binary classification and multi-classification. According to two experiments results, the style of writing of Wei Xu's poems is the most similar to that of The Golden Lotus. It is proved that among four authors, Wei Xu most likely be the author of The Golden Lotus.