Biblio

A significant challenge in modern computer security is the growing skill gap as intruder capabilities increase, making it necessary to begin automating elements of penetration testing so analysts can contend with the growing number of cyber threats. In this paper, we attempt to assist human analysts by automating a single host penetration attack. To do so, a smart agent performs different attack sequences to find vulnerabilities in a target system. As it does so, it accumulates knowledge, learns new attack sequences and improves its own internal penetration testing logic. As a result, this agent (AgentPen for simplicity) is able to successfully penetrate hosts it has never interacted with before. A computer security administrator using this tool would receive a comprehensive, automated sequence of actions leading to a security breach, highlighting potential vulnerabilities, and reducing the amount of menial tasks a typical penetration tester would need to execute. To achieve autonomy, we apply an unsupervised machine learning algorithm, Q-learning, with an approximator that incorporates a deep neural network architecture. The security audit itself is modelled as a Markov Decision Process in order to test a number of decision-making strategies and compare their convergence to optimality. A series of experimental results is presented to show how this approach can be effectively used to automate penetration testing using a scalable, i.e. not exhaustive, and adaptive approach.

In the application scenarios of cloud computing, big data, and mobile Internet, covert and diverse network attacks have become a serious problem that threatens the security of enterprises and personal information assets. Abnormal network behaviour detection based on network behaviour characteristics has become an important means to protect network security. However, existing frameworks do not make full use of the characteristics of the correlation between continuous network behaviours, and do not use an algorithm that can process time-series data or process the original feature set into time-series data to match the algorithm. This paper proposes a time-series abnormal network behaviour detection framework. The framework consists of two parts: an algorithm model (DBN-BiGRU) that combines Deep Belief Network (DBN) and Bidirectional Gated Recurrent Unit (BiGRU), and a pre-processing scheme that processes the original feature analysis files of CICIDS2017 to good time-series data. This detection framework uses past and future behaviour information to determine current behaviours, which can improve accuracy, and can adapt to the large amount of existing network traffic and high-dimensional characteristics. Finally, this paper completes the training of the algorithm model and gets the test results. Experimental results show that the prediction accuracy of this framework is as high as 99.82%, which is better than the traditional frameworks that do not use time-series information.

Database forensic investigation (DBFI) is an important area of research within digital forensics. It's importance is growing as digital data becomes more extensive and commonplace. The challenges associated with DBFI are numerous, and one of the challenges is the lack of a harmonized DBFI process for investigators to follow. In this paper, therefore, we conduct a survey of existing literature with the hope of understanding the body of work already accomplished. Furthermore, we build on the existing literature to present a harmonized DBFI process using design science research methodology. This harmonized DBFI process has been developed based on three key categories (i.e. planning, preparation and pre-response, acquisition and preservation, and analysis and reconstruction). Furthermore, the DBFI has been designed to avoid confusion or ambiguity, as well as providing practitioners with a systematic method of performing DBFI with a higher degree of certainty.

The Internet of Things (IoT) is enabling smart houses, where multiple users with complex social relationships interact with smart devices. This requires sophisticated access control specification and enforcement models, that are currently lacking. In this paper, we introduce the extended generalized role based access control (EGRBAC) model for smart home IoT. We provide a formal definition for EGRBAC and illustrate its features with a use case. A proof-of-concept demonstration utilizing AWS-IoT Greengrass is discussed in the appendix. EGRBAC is a first step in developing a comprehensive family of access control models for smart home IoT.

Hyperbox classifier is an efficient tool for modern pattern classification problems due to its transparency and rigorous use of Euclidian geometry. Fuzzy min-max (FMM) network efficiently implements the hyperbox classifier, and has been modified several times to yield better classification accuracy. However, the obtained accuracy is not up to the mark. Therefore, in this paper, a new improved FMM (IFMM) network is proposed to increase the accuracy rate. In the proposed IFMM network, a modified constraint is employed to check the expandability of a hyperbox. It also uses semiperimeter of the hyperbox along with k-nearest mechanism to select the expandable hyperbox. In the proposed IFMM, the contraction rules of conventional FMM and enhanced FMM (EFMM) are also modified using semiperimeter of a hyperbox in order to balance the size of both overlapped hyperboxes. Experimental results show that the proposed IFMM network outperforms the FMM, k-nearest FMM, and EFMM by yielding more accuracy rate with less number of hyperboxes. The proposed methods are also applied to histopathological images to know the best magnification factor for classification.

As an important type of cloud data, digital provenance is arousing increasing attention on improving system performance. Currently, provenance has been employed to provide cues regarding access control and to estimate data quality. However, provenance itself might also be sensitive information. Therefore, provenance might be encrypted and stored in the Cloud. In this paper, we provide a mechanism to classify cloud documents by searching specific keywords from their encrypted provenance, and we prove our scheme achieves semantic security. In term of application of the proposed techniques, considering that files are classified to store separately in the cloud, in order to facilitate the regulation and security protection for the files, the classification policies can use provenance as conditions to determine the category of a document. Such as the easiest sample policy goes like: the documents have been reviewed twice can be classified as “public accessible”, which can be accessed by the public.

A trust model IMPACT: Intention, Measurability, Predictability, Agility, Communication, and Transparency has been conceptualized to build human trust in autonomous agents. The six critical characteristics must be exhibited by the agents in order to gain and maintain the trust from their human partners towards an effective and collaborative team in achieving common goals. The IMPACT model guided a design of an intelligent adaptive decision aid for dynamic target engagement processes in a military context. Positive feedback from subject matter experts participated in a large scale joint exercise controlling multiple unmanned vehicles indicated the effectiveness of the decision aid. It also demonstrated the utility of the IMPACT model as design principles for building up a trusted human-agent teaming.

Recently, a large amount of research studies aiming at the privacy-preserving data publishing have been conducted. We find that most K-anonymity algorithms fail to consider the characteristics of attribute values distribution in data and the contribution value differences in quasi-identifier attributes when service-oriented. In this paper, the importance of distribution characteristics of attribute values and the differences in contribution value of quasi-identifier attributes to anonymous results are illustrated. In order to maximize the utility of released data, a service-oriented adaptive anonymity algorithm is proposed. We establish a model of reaction dispersion degree to quantify the characteristics of attribute value distribution and introduce the concept of utility weight related to the contribution value of quasi-identifier attributes. The priority coefficient and the characterization coefficient of partition quality are defined to optimize selection strategies of dimension and splitting value in anonymity group partition process adaptively, which can reduce unnecessary information loss so as to further improve the utility of anonymized data. The rationality and validity of the algorithm are verified by theoretical analysis and multiple experiments.

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such attacks are typically carried out by querying the target model using inputs that are synthetically generated or sampled from a surrogate dataset to construct a labeled dataset. The adversary can use this labeled dataset to train a clone model, which achieves a classification accuracy comparable to that of the target model. We propose "Adaptive Misinformation" to defend against such model stealing attacks. We identify that all existing model stealing attacks invariably query the target model with Out-Of-Distribution (OOD) inputs. By selectively sending incorrect predictions for OOD queries, our defense substantially degrades the accuracy of the attacker's clone model (by up to 40%), while minimally impacting the accuracy (\textbackslashtextless; 0.5%) for benign users. Compared to existing defenses, our defense has a significantly better security vs accuracy trade-off and incurs minimal computational overhead.

Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image. Adversarial examples are generated by a malicious adversary by obtaining access to the model parameters, such as gradient information, to alter the input or by attacking a substitute model and transferring those malicious examples over to attack the victim model. Specifically, one of these attack algorithms, Robust Physical Perturbations (RP2), generates adversarial images of stop signs with black and white stickers to achieve high targeted misclassification rates against standard-architecture traffic sign classifiers. In this paper, we propose BlurNet, a defense against the RP2 attack. First, we motivate the defense with a frequency analysis of the first layer feature maps of the network on the LISA dataset, which shows that high frequency noise is introduced into the input image by the RP2 algorithm. To remove the high frequency noise, we introduce a depthwise convolution layer of standard blur kernels after the first layer. We perform a blackbox transfer attack to show that low-pass filtering the feature maps is more beneficial than filtering the input. We then present various regularization schemes to incorporate this lowpass filtering behavior into the training regime of the network and perform white-box attacks. We conclude with an adaptive attack evaluation to show that the success rate of the attack drops from 90% to 20% with total variation regularization, one of the proposed defenses.

With the wide application of modern robots, more concerns have been raised on security and privacy of robotic systems and applications. Although the Robot Operating System (ROS) is commonly used on different robots, there have been few work considering the security aspects of ROS. As ROS does not employ even the basic permission control mechanism, applications can access any resources without limitation, which could result in equipment damage, harm to human, as well as privacy leakage. In this paper we propose an access control mechanism for ROS based on an extended policy-based access control (PBAC) model. Specifically, we extend ROS to add an additional node dedicated for access control so that it can provide user identity and permission management services. The proposed mechanism also allows the administrator to revoke a permission dynamically. We implemented the proposed method in ROS and demonstrated its applicability and performance through several case studies.

{Surrogate model-based optimization algorithm remains as an important solution to expensive black-box function optimization. The introduction of ensemble model enables the algorithm to automatically choose a proper model integration mode and adapt to various parameter spaces when dealing with different problems. However, this also significantly increases the computational burden of the algorithm. On the other hand, utilizing parallel computing resources and improving efficiency of black-box function optimization also require combination with surrogate optimization algorithm in order to design and realize an efficient parallel parameter space sampling mechanism. This paper makes use of parallel computing technology to speed up the weight updating related computation for the ensemble model based on Dempster-Shafer theory, and combines it with stochastic response surface method to develop a novel parallel sampling mechanism for asynchronous parameter optimization. Furthermore, it designs and implements corresponding parallel computing framework and applies the developed algorithm to quantitative trading strategy tuning in financial market. It is verified that the algorithm is both feasible and effective in actual application. The experiment demonstrates that with guarantee of optimizing performance, the parallel optimization algorithm can achieve excellent accelerating effect.

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.

The exponential growth rate of malware causes significant security concern in this digital era to computer users, private and government organizations. Traditional malware detection methods employ static and dynamic analysis, which are ineffective in identifying unknown malware. Malware authors develop new malware by using polymorphic and evasion techniques on existing malware and escape detection. Newly arriving malware are variants of existing malware and their patterns can be analyzed using the vision-based method. Malware patterns are visualized as images and their features are characterized. The alternative generation of class vectors and feature vectors using ensemble forests in multiple sequential layers is performed for classifying malware. This paper proposes a hybrid stacked multilayered ensembling approach which is robust and efficient than deep learning models. The proposed model outperforms the machine learning and deep learning models with an accuracy of 98.91%. The proposed system works well for small-scale and large-scale data since its adaptive nature of setting parameters (number of sequential levels) automatically. It is computationally efficient in terms of resources and time. The method uses very fewer hyper-parameters compared to deep neural networks.

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.

Engineering complex distributed systems is challenging. Recent solutions for the development of cyber-physical systems (CPS) in industry tend to rely on architectural designs based on service orientation, where the constituent components are deployed according to their service behavior and are to be understood as loosely coupled and mostly independent. In this paper, we develop a workflow that combines contract-based and CPS model-based specifications with service orientation, and analyze the resulting model using fault injection to assess the dependability of the systems. Compositionality principles based on the contract specification help us to make the analysis practical. The presented techniques are evaluated on two case studies.

Cyber Physical Systems (CPS)-Internet of Things (IoT) enabled healthcare services and infrastructures improve human life, but are vulnerable to a variety of emerging cyber-attacks. Cybersecurity specialists are finding it hard to keep pace of the increasingly sophisticated attack methods. There is a critical need for innovative cognitive cybersecurity for CPS-IoT enabled healthcare ecosystem. This paper presents a cognitive cybersecurity framework for simulating the human cognitive behaviour to anticipate and respond to new and emerging cybersecurity and privacy threats to CPS-IoT and critical infrastructure systems. It includes the conceptualisation and description of a layered architecture which combines Artificial Intelligence, cognitive methods and innovative security mechanisms.

More and more security and privacy issues are arising as new technologies, such as big data and cloud computing, are widely applied in nowadays. For decreasing the privacy breaches in access control system under opening and cross-domain environment. In this paper, we suggest a game and risk based access model for privacy preserving by employing Shannon information and game theory. After defining the notions of Privacy Risk and Privacy Violation Access, a high-level framework of game theoretical risk based access control is proposed. Further, we present formulas for estimating the risk value of access request and user, construct and analyze the game model of the proposed access control by using a multi-stage two player game. There exists sub-game perfect Nash equilibrium each stage in the risk based access control and it's suitable to protect the privacy by limiting the privacy violation access requests.

Cloud computing is not adequately secure due to the currently used traditional trust methods such as global trust model and local trust model. These are prone to security vulnerabilities. This paper introduces a trust model based on the fuzzy mathematics and gray relational theory. Fuzzy mathematics and gray relational analysis (Fuzzy-GRA) aims to improve the poor dynamic adaptability of cloud computing. Fuzzy-GRA platform is used to test and validate the behavior of the model. Furthermore, our proposed model is compared to other known models. Based on the experimental results, we prove that our model has the edge over other existing models.

The notion of attribute-based encryption with outsourced decryption (OD-ABE) was proposed by Green, Hohenberger, and Waters. In OD-ABE, the ABE ciphertext is converted to a partially-decrypted ciphertext that has a shorter bit length and a faster decryption time than that of the ABE ciphertext. In particular, the transformation can be performed by a powerful third party with a public transformation key. In this paper, we propose a generic approach for constructing ABE with outsourced decryption from standard ABE, as long as the later satisfies some additional properties. Its security can be reduced to the underlying standard ABE in the selective security model by a black-box way. To avoid the drawback of selective security in practice, we further propose a modified decryption outsourcing mode so that our generic construction can be adapted to satisfying adaptive security. This partially solves the open problem of constructing an OD-ABE scheme, and its adaptive security can be reduced to the underlying ABE scheme in a black-box way. Then, we present some concrete constructions that not only encompass existing ABE outsourcing schemes of Green et al., but also result in new selectively/adaptively-secure OD-ABE schemes with more efficient transformation key generation algorithm. Finally, we use the PBC library to test the efficiency of our schemes and compare the results with some previous ones, which shows that our schemes are more efficient in terms of decryption outsourcing and transformation key generation.

Continuous and adaptive learning is an effective learning approach when dealing with highly dynamic and changing scenarios, where concept drift often happens. In a continuous, stream or adaptive learning setup, new measurements arrive continuously and there are no boundaries for learning, meaning that the learning model has to decide how and when to (re)learn from these new data constantly. We address the problem of adaptive and continual learning for network security, building dynamic models to detect network attacks in real network traffic. The combination of fast and big network measurements data with the re-training paradigm of adaptive learning imposes complex challenges in terms of data processing speed, which we tackle by relying on big data platforms for parallel stream processing. We build and benchmark different adaptive learning models on top of a novel big data analytics platform for network traffic monitoring and analysis tasks, and show that high speed-up computations (as high as × 6) can be achieved by parallelizing off-the-shelf stream learning approaches.

Autonomic resource management for distributed edge computing systems provides an effective means of enabling dynamic placement and adaptation in the face of network changes, load dynamics, and failures. However, adaptation in-and-of-itself offers a side channel by which malicious entities can extract valuable information. An attacker can take advantage of autonomic resource management techniques to fool a system into misallocating resources and crippling applications. Using a few scenarios, we outline how attacks can be launched using partial knowledge of the resource management substrate - with as little as a single compromised node. We argue that any system that provides adaptation must consider resource management as an attack surface. As such, we propose ADAPT2, a framework that incorporates concepts taken from Moving-Target Defense and state estimation techniques to ensure correctness and obfuscate resource management, thereby protecting valuable system and application information from leaking.

Incident prioritization is nowadays a part of many approaches and tools for network security and risk management. However, the dynamic nature of the problem domain is often unaccounted for. That is, the prioritization is typically based on a set of static calculations, which are rarely adjusted. As a result, incidents are incorrectly prioritized, leading to an increased and misplaced effort in the incident response. A higher degree of automation could help to address this problem. In this paper, we explicitly consider flaws in the prioritization an unalterable circumstance. We propose an adaptive incident prioritization, which allows to automate certain tasks for the prioritization model management in order to continuously assess and improve a prioritization model. At the same time, we acknowledge the human analyst as the focal point and propose to keep the human in the loop, among others by treating understandability as a crucial requirement.

Cyber physical system (CPS) is often deployed at safety-critical key infrastructures and fields, fault tolerance policies are extensively applied in CPS systems to improve its credibility; the same physical backup of hardware redundancy (SPB) technology is frequently used for its simple and reliable implementation. To resolve challenges faced with in simulation test of SPB-CPS, this paper dynamically determines the test resources matched with the CPS scale by using the adaptive allocation policies, establishes the hierarchical models and inter-layer message transmission mechanism. Meanwhile, the collaborative simulation time sequence push strategy and the node activity test mechanism based on the sliding window are designed in this paper to improve execution efficiency of the simulation test. In order to validate effectiveness of the method proposed in this paper, we successfully built up a fault-tolerant CPS simulation platform. Experiments showed that it can improve the SPB-CPS simulation test efficiency.

The intelligent production line is a complex application with a large number of independent equipment network integration. In view of the characteristics of CPS, the existing modeling methods cannot well meet the application requirements of large scale high-performance system. a formal simulation verification framework and verification method are designed for the performance constraints such as the real-time and security of the intelligent production line based on soft bus. A model-based service-oriented integration approach is employed, which adopts a model-centric way to automate the development course of the entire software life cycle. Developing experience indicate that the proposed approach based on the formal modeling and verification framework in this paper can improve the performance of the system, which is also helpful to achieve the balance of the production line and maintain the reasonable use rate of the processing equipment.