Biblio

This work introduces methods that unlock a series of applications for decision trees and neural networks in power system optimization. Capturing constraints that were impossible to capture before in a scalable way, we use decision trees (or neural networks) to extract an accurate representation of the non-convex feasible region which is characterized by both algebraic and differential equations. Applying an exact transformation, we convert the information encoded in the decision trees and the neural networks to linear decision rules that we incorporate as conditional constraints in an optimization problem (MILP or MISOCP). Our approach introduces a framework to unify security considerations with electricity market operations, capturing not only steady-state but also dynamic stability constraints in power system optimization, and has the potential to eliminate redispatching costs, leading to savings of millions of euros per year.

Formal languages are ubiquitous wherever software systems need to exchange or store data. Unparsing into and parsing from such languages is an error-prone process that has spawned an entire class of security vulnerabilities. There has been ample research into finding vulnerabilities on the parser side, but outside of language specific approaches, few techniques targeting unparser vulnerabilities exist. This work presents a language-agnostic approach for spotting injection vulnerabilities in unparsers. It achieves this by mining unparse trees using dynamic taint analysis to extract language keywords, which are leveraged for guided fuzzing. Vulnerabilities can thus be found without requiring prior knowledge about the formal language, and in fact, the approach is even applicable where no specification thereof exists at all. This empowers security researchers and developers alike to gain deeper understanding of unparser implementations through examination of the unparse trees generated by the approach, as well as enabling them to find new vulnerabilities in poorly-understood software. This work presents a language-agnostic approach for spotting injection vulnerabilities in unparsers. It achieves this by mining unparse trees using dynamic taint analysis to extract language keywords, which are leveraged for guided fuzzing. Vulnerabilities can thus be found without requiring prior knowledge about the formal language, and in fact, the approach is even applicable where no specification thereof exists at all. This empowers security researchers and developers alike to gain deeper understanding of unparser implementations through examination of the unparse trees generated by the approach, as well as enabling them to find new vulnerabilities in poorly-understood software.

Vehicular networks are vulnerable to a variety of internal attacks. Misbehavior Detection Systems (MDS) are preferred over the cryptography solutions to detect such attacks. However, the existing misbehavior detection systems are static and do not adapt to the context of vehicles. To this end, we exploit the Software-Defined Networking (SDN) paradigm to propose a context-aware MDS. Based on the context, our proposed system can tune security parameters to provide accurate detection with low false positives. Our system is Sybil attack-resistant and compliant with vehicular privacy standards. The simulation results show that, under different contexts, our system provides a high detection ratio and low false positives compared to a static MDS.

An adversarial attack is an algorithm that perturbs the input of a machine learning model in an intelligent way in order to change the output of the model. An important property of adversarial attacks is transferability. According to this property, it is possible to generate adversarial perturbations on one model and apply it the input to fool the output of a different model. Our work focuses on studying the transferability of adversarial attacks in sound event classification. We are able to demonstrate differences in transferability properties from those observed in computer vision. We show that dataset normalization techniques such as z-score normalization does not affect the transferability of adversarial attacks and we show that techniques such as knowledge distillation do not increase the transferability of attacks.

In this paper, we apply machine learning to distributed private data owned by multiple data owners, entities with access to non-overlapping training datasets. We use noisy, differentially-private gradients to minimize the fitness cost of the machine learning model using stochastic gradient descent. We quantify the quality of the trained model, using the fitness cost, as a function of privacy budget and size of the distributed datasets to capture the trade-off between privacy and utility in machine learning. This way, we can predict the outcome of collaboration among privacy-aware data owners prior to executing potentially computationally-expensive machine learning algorithms. Particularly, we show that the difference between the fitness of the trained machine learning model using differentially-private gradient queries and the fitness of the trained machine model in the absence of any privacy concerns is inversely proportional to the size of the training datasets squared and the privacy budget squared. We successfully validate the performance prediction with the actual performance of the proposed privacy-aware learning algorithms, applied to: financial datasets for determining interest rates of loans using regression; and detecting credit card frauds using support vector machines.

This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment.

Today, Internet of Things (IoT) devices mostly operate in enclosed, proprietary environments. To unfold the full potential of IoT applications, a unifying and permissionless environment is crucial. All IoT devices, even unknown to each other, would be able to trade services and assets across various domains. In order to realize those applications, uniquely resolvable identities are essential. However, quantifiable trust in identities and their authentication are not trivially provided in such an environment due to the absence of a trusted authority. This research presents a new identity and trust framework for IoT devices, based on Distributed Ledger Technology (DLT). IoT devices assign identities to themselves, which are managed publicly and decentralized on the DLT's network as Self Sovereign Identities (SSI). In addition to the Identity Management System (IdMS), the framework provides a Web of Trust (WoT) approach to enable automatic trust rating of arbitrary identities. For the framework we used the IOTA Tangle to access and store data, achieving high scalability and low computational overhead. To demonstrate the feasibility of our framework, we provide a proof-of-concept implementation and evaluate the set objectives for real world applicability as well as the vulnerability against common threats in IdMSs and WoTs.

The regularity of devastating cyber-attacks has made cybersecurity a grand societal challenge. Many cybersecurity professionals are closely examining the international Dark Web to proactively pinpoint potential cyber threats. Despite its potential, the Dark Web contains hundreds of thousands of non-English posts. While machine translation is the prevailing approach to process non-English text, applying MT on hacker forum text results in mistranslations. In this study, we draw upon Long-Short Term Memory (LSTM), Cross-Lingual Knowledge Transfer (CLKT), and Generative Adversarial Networks (GANs) principles to design a novel Adversarial CLKT (A-CLKT) approach. A-CLKT operates on untranslated text to retain the original semantics of the language and leverages the collective knowledge about cyber threats across languages to create a language invariant representation without any manual feature engineering or external resources. Three experiments demonstrate how A-CLKT outperforms state-of-the-art machine learning, deep learning, and CLKT algorithms in identifying cyber-threats in French and Russian forums.

We propose a novel attestation architecture for the Internet of Things (IoT). Our distributed attestation network (DAN) utilizes blockchain technology to store and share device information. We present the design of this new attestation architecture as well as a prototype system chosen to emulate an IoT deployment with a network of Raspberry Pi, Infineon TPMs, and a Hyperledger Fabric blockchain.

IoT data marketplaces are being developed to help cities and communities create large scale IoT applications. Such data marketplaces let the IoT device owners sell their data to the application developers. Following this application development model, the application developers need not deploy their own IoT devices when developing IoT applications; instead, they can buy data from a data marketplace. In a marketplace-based IoT application, the application developers are making critical business and operation decisions using the data produced by seller's IoT devices. Under these circumstances, it is crucial to verify and validate the security of IoT devices.In this paper, we assess the security of IoT data marketplaces. In particular, we discuss what kind of vulnerabilities exist in IoT data marketplaces using the well-known STRIDE model, and present a security assessment and certification framework for IoT data marketplaces to help the device owners to examine the security vulnerabilities of their devices. Most importantly, our solution certifies the IoT devices when they connect to the data marketplace, which helps the application developers to make an informed decision when buying and consuming data from a data marketplace. To demonstrate the effectiveness of the proposed approach, we have developed a proof-of-concept using I3 (Intelligent IoT Integrator), which is an open-source IoT data marketplace developed at the University of Southern California, and IoTcube, which is a vulnerability detection toolkit developed by researchers at Korea University. Through this work, we show that it is possible to increase the reliability of a IoT data marketplace while not damaging the convenience of the users.

The mechanism of peers randomly choosing logical neighbors without any knowledge about underlying physical topology can cause a delay overhead in information propagation which makes the system vulnerable to double spend attacks. This paper introduces a proximity-aware extensions to the current Bitcoin protocol, named Master Node Based Clustering (MNBC). The ultimate purpose of the proposed protocol is to improve the information propagation delay in the Bitcoin network.

Robot Operating System (ROS) is becoming more and more important and is used widely by developers and researchers in various domains. One of the most important fields where it is being used is the self-driving cars industry. However, this framework is far from being totally secure, and the existing security breaches do not have robust solutions. In this paper we focus on the camera vulnerabilities, as it is often the most important source for the environment discovery and the decision-making process. We propose an unsupervised anomaly detection tool for detecting suspicious frames incoming from camera flows. Our solution is based on spatio-temporal autoencoders used to truthfully reconstruct the camera frames and detect abnormal ones by measuring the difference with the input. We test our approach on a real-word dataset, i.e. flows coming from embedded cameras of self-driving cars. Our solution outperforms the existing works on different scenarios.

With the rapid technological advancement of the universal internet of vehicles (UIoV), it becomes crucial to ensure safe and secure communication over the network, in an effort to achieve the implementation objective of UIoV effectively. A UIoV is characterized by highly dynamic topology, scalability, and thus vulnerable to various types of security and privacy attacks (i.e., replay attack, impersonation attack, man-in-middle attack, non-repudiation, and modification). Since the components of UIoV are constrained by numerous factors (e.g., low memory devices, low power), which makes UIoV highly susceptible. Therefore, existing schemes to address the privacy and security facets of UIoV exhibit an enormous scope of improvement in terms of time complexity and efficiency. This paper presents a lightweight authentication and batch verification scheme (LABVS) for UIoV using a bilinear map and cryptographic operations (i.e., one-way hash function, concatenation, XOR) to minimize the rate of message loss occurred due to delay in response time as in single message verification scheme. Subsequently, the scheme results in a high level of security and privacy. Moreover, the performance analysis substantiates that LABVS minimizes the computational delay and has better performance in the delay-sensitive network in terms of security and privacy as compared to the existing schemes.

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

Due to the wide adoption of IoT/CPS systems, embedded devices (IoT frontends) become increasingly connected and mission-critical, which in turn has attracted advanced attacks (e.g., control-flow hijacks and data-only attacks). Unfortunately, IoT backends (e.g., remote controllers or in-cloud services) are unable to detect if such attacks have happened while receiving data, service requests, or operation status from IoT devices (remotely deployed embedded devices). As a result, currently, IoT backends are forced to blindly trust the IoT devices that they interact with.To fill this void, we first formulate a new security property for embedded devices, called "Operation Execution Integrity" or OEI. We then design and build a system, OAT, that enables remote OEI attestation for ARM-based bare-metal embedded devices. Our formulation of OEI captures the integrity of both control flow and critical data involved in an operation execution. Therefore, satisfying OEI entails that an operation execution is free of unexpected control and data manipulations, which existing attestation methods cannot check. Our design of OAT strikes a balance between prover's constraints (embedded devices' limited computing power and storage) and verifier's requirements (complete verifiability and forensic assistance). OAT uses a new control-flow measurement scheme, which enables lightweight and space-efficient collection of measurements (97% space reduction from the trace-based approach). OAT performs the remote control-flow verification through abstract execution, which is fast and deterministic. OAT also features lightweight integrity checking for critical data (74% less instrumentation needed than previous work). Our security analysis shows that OAT allows remote verifiers or IoT backends to detect both controlflow hijacks and data-only attacks that affect the execution of operations on IoT devices. In our evaluation using real embedded programs, OAT incurs a runtime overhead of 2.7%.

The root causes of many security vulnerabilities include a pernicious combination of two problems, often regarded as inescapable aspects of computing. First, the protection mechanisms provided by the mainstream processor architecture and C/C++ language abstractions, dating back to the 1970s and before, provide only coarse-grain virtual-memory-based protection. Second, mainstream system engineering relies almost exclusively on test-and-debug methods, with (at best) prose specifications. These methods have historically sufficed commercially for much of the computer industry, but they fail to prevent large numbers of exploitable bugs, and the security problems that this causes are becoming ever more acute.In this paper we show how more rigorous engineering methods can be applied to the development of a new security-enhanced processor architecture, with its accompanying hardware implementation and software stack. We use formal models of the complete instruction-set architecture (ISA) at the heart of the design and engineering process, both in lightweight ways that support and improve normal engineering practice - as documentation, in emulators used as a test oracle for hardware and for running software, and for test generation - and for formal verification. We formalise key intended security properties of the design, and establish that these hold with mechanised proof. This is for the same complete ISA models (complete enough to boot operating systems), without idealisation.We do this for CHERI, an architecture with hardware capabilities that supports fine-grained memory protection and scalable secure compartmentalisation, while offering a smooth adoption path for existing software. CHERI is a maturing research architecture, developed since 2010, with work now underway on an Arm industrial prototype to explore its possible adoption in mass-market commercial processors. The rigorous engineering work described here has been an integral part of its development to date, enabling more rapid and confident experimentation, and boosting confidence in the design.

The paper presents a comprehensive model of cybersecurity threats for a system of autonomous and remotely controlled vehicles (AV) in the environment of a smart city. The main focus in the security context is given to the “integrity” property. That property is of higher importance for industrial control systems in comparison with other security properties (availability and confidentiality). The security graph, which is part of the model, is dynamic, and, in real cases, its analysis may require significant computing resources for AV systems with a large number of assets and connections. The simplified example of the security graph for the AV system is presented.

Intrusion Detection Systems (IDS) are the systems that detect and block any potential threats (e.g. DDoS attacks) in the network. In this project, we explore the performance of several machine learning techniques when used as parts of an IDS. We experiment with the CICIDS2017 dataset, one of the biggest and most complete IDS datasets in terms of having a realistic background traffic and incorporating a variety of cyber attacks. The techniques we present are applicable to any IDS dataset and can be used as a basis for deploying a real time IDS in complex environments.

Classification of Misbehaving Nodes in wireless mobile adhoc networks (MANET) by applying machine learning techniques is an attempt to enhance security by detecting the presence of malicious nodes. MANETs are prone to many security vulnerabilities due to its significant features. The paper compares two machine learning techniques namely Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) and finds out the best technique to detect the misbehaving nodes. This paper is simulated with an on-demand routing protocol in NS2.35 and the results can be compared using parameters like packet Delivery Ratio (PDR), End-To-End delay, Average Throughput.

Natural disasters and cyber intrusions threaten the normal operation of the critical electric grid infrastructure. There is still no widely accepted methodology to quantify the resilience in power systems. In this work, power system resiliency refers to the ability of the system to keep provide energy to the critical load even with adverse events. A significant amount of work has been done to quantify the resilience for distribution systems. Even though critical loads are located in distribution system, transmission system play a critical role in supplying energy to distribution feeder in addition to the Distributed Energy Resources (DERs). This work focuses on developing a framework to quantify the resiliency of cyber-physical transmission systems. Quantifying the resiliency of the transmission network, is important to determine and devise suitable control mechanisms to minimize the effects of undesirable events in the power grid. The proposed metric is based on both system infrastructure and with changing operating conditions. A graphical analysis along with measure of critical parameters of the network is performed to quantify the redundancy and vulnerabilities in the physical network of the system. A similar approach is used to quantify the cyber-resiliency. The results indicate the capability of the proposed framework to quantify cyber-physical resilience of the transmission systems.

Wireless Sensor Network (WSN) is a heterogeneous type of network consisting of scattered sensor nodes and working together for data collection, processing, and transmission functions[1], [2]. Because WSN is widely used in vital matters, aspects of its security must also be considered. There are many types of attacks that might be carried out to disrupt WSN networks. The methods of attack that exist in WSN include jamming attack, tampering, Sybil attack, wormhole attack, hello flood attack, and, blackhole attack[3]. Blackhole attacks are one of the most dangerous attacks on WSN networks. Enhanced Check Agent method is designed to detect black hole attacks by sending a checking agent to record nodes that are considered black okay. The implementation will be tested right on a wireless sensor network using ZigBee technology. Network topology uses a mesh where each node can have more than one routing table[4]. The Enhanced Check Agent method can increase throughput to 100 percent.

Lin et al.'s scheme is a hash function Message Authentication Codes (MAC) block cipher based scheme that's composed of the compression function. Fixed point messages have been found on SMALLPRESENT-[s] algorithm. The vulnerability of block cipher algorithm against fixed point attacks can affect the vulnerability of block cipher based hash function schemes. This paper applies fixed point attack against Lin et al.'s modified scheme based on SMALLPRESENT-[8] algorithm. Fixed point attack was done using fixed point message from SMALLPRESENT-[8] algorithm which used as Initial Value (IV) on the scheme branch. The attack result shows that eight fixed point messages are successfully discovered on the B1 branch. The fixed point messages discovery on B1 and B2 branches form 18 fixed point messages on Lin et al.'s modified scheme with different IVs and keys. The discovery of fixed point messages shows that Lin et al.'s modified scheme is vulnerable to fixed point attack.

Smart meters (SMs) can pose privacy threats for consumers, an issue that has received significant attention in recent years. This paper studies the impact of Side Information (SI) on the performance of possible attacks to real-time privacy-preserving algorithms for SMs. In particular, we consider a deep adversarial learning framework, in which the desired releaser, which is a Recurrent Neural Network (RNN), is trained by fighting against an adversary network until convergence. To define the objective for training, two different approaches are considered: the Causal Adversarial Learning (CAL) and the Directed Information (DI)-based learning. The main difference between these approaches relies on how the privacy term is measured during the training process. The releaser in the CAL method, disposing of supervision from the actual values of the private variables and feedback from the adversary performance, tries to minimize the adversary log-likelihood. On the other hand, the releaser in the DI approach completely relies on the feedback received from the adversary and is optimized to maximize its uncertainty. The performance of these two algorithms is evaluated empirically using real-world SMs data, considering an attacker with access to SI (e.g., the day of the week) that tries to infer the occupancy status from the released SMs data. The results show that, although they perform similarly when the attacker does not exploit the SI, in general, the CAL method is less sensitive to the inclusion of SI. However, in both cases, privacy levels are significantly affected, particularly when multiple sources of SI are included.

Verifiability is one of the parameters in e-voting that can increase confidence in voting technology with several parties ensuring that voters do not change their votes. Voting has become an important part of the democratization system, both to make choices regarding policies, to elect representatives to sit in the representative assembly, and to elect leaders. the more voters and the wider the distribution, the more complex the social life, and the need to manage the voting process efficiently and determine the results more quickly, electronic-based voting (e-Voting) is becoming a more promising option. The level of confidence in voting depends on the capabilities of the system. E-voting must have parameters that can be used as guidelines, which include the following: Accuracy, Invulnerability, Privacy and Verifiability. The implementation of the simple verifiability metric to measure the degree of verifiability in the e-voting protocol, the researchers can calculate the degree of verifiability in the e-voting protocol and the researchers have been able to assess the proposed e-voting protocol with the standard of the best degree of verifiability is 1, where the value of 1 is is absolutely verified protocol.

A continually growing number of sensors is required for monitoring industrial processes and for continuous data acquisition from industrial plants and devices. The cabling of sensors represent a considerable effort and potential source of error, which can be avoided by using wireless sensor nodes. These wireless sensor nodes form a wireless sensor network (WSN) to efficiently transmit data to the destination. For the acceptance of WSNs in industry, it is important to build up networks with high trustworthiness. The trustworthiness of the WSN depends not only on a secure wireless communication but also on the ability to detect modifications at the wireless sensor nodes itself. This paper presents the enhancement of the WSN's trustworthiness using an optical localization system. It can be used for the preparation phase of the WSN and also during operation to track the positions of the wireless sensor nodes and detect spatial modification. The location information of the sensor nodes can also be used to rate their trustworthiness.