Biblio

The increasing data generation rate and the proliferation of deep learning applications have led to the development of machine learning-as-a-service (MLaaS) platforms by major Cloud providers. The existing MLaaS platforms, however, fall short in protecting the clients’ private data. Recent distributed MLaaS architectures such as federated learning have also shown to be vulnerable against a range of privacy attacks. Such vulnerabilities motivated the development of privacy-preserving MLaaS techniques, which often use complex cryptographic prim-itives. Such approaches, however, demand abundant computing resources, which undermine the low-latency nature of evolving applications such as autonomous driving.To address these challenges, we propose SCLERA–an efficient MLaaS framework that utilizes trusted execution environment for secure execution of clients’ workloads. SCLERA features a set of optimization techniques to reduce the computational complexity of the offloaded services and achieve low-latency inference. We assessed SCLERA’s efficacy using image/video analytic use cases such as scene detection. Our results show that SCLERA achieves up to 23× speed-up when compared to the baseline secure model execution.

State-of-the-art approaches in gait analysis usually rely on one isolated tracking system, generating insufficient data for complex use cases such as sports, rehabilitation, and MedTech. We address the opportunity to comprehensively understand human motion by a novel data model combining several motion-tracking methods. The model aggregates pose estimation by captured videos and EMG and EIT sensor data synchronously to gain insights into muscle activities. Our demonstration with biceps curl and sitting/standing pose generates time-synchronous data and delivers insights into our experiment’s usability, advantages, and challenges.

With the development of 5G networking technology on the Internet of Vehicle (IoV), there are new opportunities for numerous cyber-attacks, such as in-vehicle attacks like hijacking occurrences and data theft. While numerous attempts have been made to protect against the potential attacks, there are still many unsolved problems such as developing a fine-grained access control system. This is reflected by the granularity of security as well as the related data that are hosted on these platforms. Among the most notable trends is the increased usage of smart devices, IoV, cloud services, emerging technologies aim at accessing, storing and processing data. Most popular authentication protocols rely on knowledge-factor for authentication that is infamously known to be vulnerable to subversions. Recently, the zero-trust framework has drawn huge attention; there is an urgent need to develop further the existing Continuous Authentication (CA) technique to achieve the zero-trustiness framework. In this paper, firstly, we develop the static authentication process and propose a secured protocol to generate the smart key for user to unlock the vehicle. Then, we proposed a novel and secure continuous authentication system for IoVs. We present the proof-of-concept of our CA scheme by building a prototype that leverages the commodity fingerprint sensors, NFC, and smartphone. Our evaluations in real-world settings demonstrate the appropriateness of CA scheme and security analysis of our proposed protocol for digital key suggests its enhanced security against the known attack-vector.

With their variety of application verticals, smart cities represent a killer scenario for Cloud-IoT computing, e.g. fog computing. Such applications require a management capable of satisfying all their requirements through suitable service placements, and of balancing among QoS-assurance, operational costs, deployment security and, last but not least, energy consumption and carbon emissions. This keynote discusses these aspects over a motivating use case and points to some open challenges.

The marine and maritime domain is well represented in the Sustainable Development Goals (SDG) envisaged by the United Nations, which aim at conserving and using the oceans, seas and their resources for sustainable development. At the same time, there is a need for improved safety in navigation, especially in coastal areas. Up to date, there exist operational services based on advanced technologies, including remote sensing and in situ monitoring networks which provide aid to the navigation and control over the environment for its preservation. Yet, the possibilities offered by crowdsensing have not yet been fully explored. This paper addresses this issue by presenting an app based on a crowdsensing approach for improved safety and awareness at sea. The app can be integrated into more comprehensive systems and frameworks for environmental monitoring as envisaged in our future work.

The distributed energy resources (DERs) have significantly stimulated the development of decentralized energy system and changed the way how the energy system works. In recent years, peer-to-peer (P2P) trading has drawn attention as a promising alternative for prosumers to engage with the energy market more actively, particular by using the emerging blockchain technology. Blockchain can securely hold critical information and store data in blocks linking with chain, providing a desired platform for the P2P energy trading. This paper provides a detailed description of blockchain-enabled P2P energy trading, its essential components, and how it can be implemented within the local energy market An analysis of potential threats during blockchain-enabled P2P energy trading is also performed, which subsequently results in a list of operation and privacy requirements suggested to be implemented in the local energy market.

Lock design is an important mechanism for scheduling management and security protection in operating systems. However, there is no effective way to identify the differences and connections among lock models, and users need to spend considerable time to understand different lock architectures. In this paper, we propose a classification scheme that abstracts lock design into three types of models: basic spinlock, semaphore amount extension, lock chain structure, and verify the effectiveness of these three types of lock models in the context of current mainstream applications. We also investigate the specific details of applying this classification method, which can be used as a reference for developers to design lock models, thus shorten the software development cycle.

Edge detection based embedding techniques are famous for data security and image quality preservation. These techniques use diverse edge detectors to classify edge and non-edge pixels in an image and then implant secrets in one or both of these classes. Image with conceived data is called stego image. It is noticeable that none of such researches tries to reform the original image from the stego one. Rather, they devote their concentration to extract the hidden message only. This research presents a solution to the raised reversibility problem. Like the others, our research, first, applies an edge detector e.g., canny, in a cover image. The scheme next collects \$n\$-LSBs of each of edge pixels and finally, concatenates them with encrypted message stream. This method applies a lossless compression algorithm to that processed stream. Compression factor is taken such a way that the length of compressed stream does not exceed the length of collected LSBs. The compressed message stream is then implanted only in the edge pixels by \$n\$-LSB substitution method. As the scheme does not destroy the originality of non-edge pixels, it presents better stego quality. By incorporation the mechanisms of encryption, concatenation, compression and \$n\$-LSB, the method has enriched the security of implanted data. The research shows its effectiveness while implanting a small sized message.

Minimizing embedding impact model of steganography has good performance for steganalysis detection. By using effective distortion cost function and coding method, steganography under this model becomes the mainstream embedding framework recently. In this paper, to improve the anti-detection performance, a new steganography optimization model by constructing a reference cover is proposed. First, a reference cover is construed by performing a filtering operation on the cover image. Then, by minimizing the residual between the reference cover and the original cover, the optimization function is formulated considering the effect of different modification directions. With correcting the distortion cost of +1 and \_1 modification operations, the stego image obtained by the proposed method is more consistent with the natural image. Finally, by applying the proposed framework to the cost function of the well-known HILL embedding, experimental results show that the anti-detection performance of the proposed method is better than the traditional method.

In our time the rapid growth of internet and digital communications has been required to be protected from illegal users. It is important to secure the information transmitted between the sender and receiver over the communication channels such as the internet, since it is a public environment. Cryptography and Steganography are the most popular techniques used for sending data in secrete way. In this paper, we are proposing a new algorithm that combines both cryptography and steganography in order to increase the level of data security against attackers. In cryptography, we are using affine hill cipher method; while in steganography we are using Hybrid edge detection with LSB to hide the message. Our paper shows how we can use image edges to hide text message. Grayscale images are used for our experiments and a comparison is developed based on using different edge detection operators such as (canny-LoG ) and (Canny-Sobel). Their performance is measured using PSNR (Peak Signal to Noise ratio), MSE (Mean Squared Error) and EC (Embedding Capacity). The results indicate that, using hybrid edge detection (canny- LoG) with LSB for hiding data could provide high embedding capacity than using hybrid edge detection (canny- Sobel) with LSB. We could prove that hiding in the image edge area could preserve the imperceptibility of the Stego-image. This paper has also proved that the secrete message was extracted successfully without any distortion.

Ethical bias in machine learning models has become a matter of concern in the software engineering community. Most of the prior software engineering works concentrated on finding ethical bias in models rather than fixing it. After finding bias, the next step is mitigation. Prior researchers mainly tried to use supervised approaches to achieve fairness. However, in the real world, getting data with trustworthy ground truth is challenging and also ground truth can contain human bias. Semi-supervised learning is a technique where, incrementally, labeled data is used to generate pseudo-labels for the rest of data (and then all that data is used for model training). In this work, we apply four popular semi-supervised techniques as pseudo-labelers to create fair classification models. Our framework, Fair-SSL, takes a very small amount (10%) of labeled data as input and generates pseudo-labels for the unlabeled data. We then synthetically generate new data points to balance the training data based on class and protected attribute as proposed by Chakraborty et al. in FSE 2021. Finally, classification model is trained on the balanced pseudo-labeled data and validated on test data. After experimenting on ten datasets and three learners, we find that Fair-SSL achieves similar performance as three state-of-the-art bias mitigation algorithms. That said, the clear advantage of Fair-SSL is that it requires only 10% of the labeled training data. To the best of our knowledge, this is the first SE work where semi-supervised techniques are used to fight against ethical bias in SE ML models. To facilitate open science and replication, all our source code and datasets are publicly available at https://github.com/joymallyac/FairSSL. CCS CONCEPTS • Software and its engineering → Software creation and management; • Computing methodologies → Machine learning. ACM Reference Format: Joymallya Chakraborty, Suvodeep Majumder, and Huy Tu. 2022. Fair-SSL: Building fair ML Software with less data. In International Workshop on Equitable Data and Technology (FairWare ‘22), May 9, 2022, Pittsburgh, PA, USA. ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3524491.3527305

In recent years, the blackout accident shows that the cause of power failure is not only in the power network, but also in the cyber network. Aiming at the problem of cyber network fault Cyber-physical power systems, combined with the structure and functional attributes of cyber network, the comprehensive criticality of information node is defined. By evaluating the vulnerability of ieee39 node system, it is found that the fault of high comprehensive criticality information node will cause greater load loss to the system. The simulation results show that the comprehensive criticality index can effectively identify the key nodes of the cyber network.

Security is of vital importance in wireless industrial communication systems. When spoofing attacking has occurred, leading to economic losses or even safety accidents. So as to address the concern, existing approaches mainly rely on traditional cryptographic algorithms. However, these methods cannot meet the needs of short delay and lightweight. In this paper, we propose a CSI-based PHY-layer security authentication scheme to detect spoofing detection. The main idea takes advantage of the uncorrelated nature of wireless channels to the identification of spoofing nodes in the physical layer. We demonstrate a MIMO-OFDM based spoofing detection prototype in industrial environments. Firstly, utilizing Universal Software Radio Peripheral (USRPs) to establish MIMO-OFDM communication systems is presented. Secondly, our proposed security scheme of CSI-based PHY-layer authentication is demonstrated. Finally, the effectiveness of the proposed approach has been verified via attack experiments.

The increasing use of Infrastructure as Code (IaC) in DevOps leads to benefits in speed and reliability of deployment operation, but extends to infrastructure challenges typical of software systems. IaC scripts can contain defects that result in security and reliability issues in the deployed infrastructure: techniques for detecting and preventing them are needed. We analyze and survey the current state of research in this respect by conducting a literature review on static analysis techniques for IaC. We describe analysis techniques, defect categories and platforms targeted by tools in the literature.

Synthetic static code analysis test suites are important to test the basic functionality of tools. We present a framework that uses different source code patterns to generate Cross Site Scripting and SQL injection test cases. A decision tree is used to determine if the test cases are vulnerable. The test cases are split into two test suites. The first test suite contains 258,432 test cases that have influence on the decision trees. The second test suite contains 20 vulnerable test cases with different data flow patterns. The test cases are scanned with two commercial static code analysis tools to show that they can be used to benchmark and identify problems of static code analysis tools. Expert interviews confirm that the decision tree is a solid way to determine the vulnerable test cases and that the test suites are relevant.

Static analyzers have become increasingly popular both as developer tools and as subjects of empirical studies. Whereas static analysis tools exist for disparate programming languages, the bulk of the empirical research has focused on the popular Java programming language. In this paper, we investigate to what extent some known results about using static analyzers for Java change when considering C\#-another popular object-oriented language. To this end, we combine two replications of previous Java studies. First, we study which static analysis tools are most widely used among C\# developers, and which warnings are more commonly reported by these tools on open-source C\# projects. Second, we develop and empirically evaluate EagleRepair: a technique to automatically fix code in response to static analysis warnings; this is a replication of our previous work for Java [20]. Our replication indicates, among other things, that 1) static code analysis is fairly popular among C\# developers too; 2) Re-Sharper is the most widely used static analyzer for C\#; 3) several static analysis rules are commonly violated in both Java and C\# projects; 4) automatically generating fixes to static code analysis warnings with good precision is feasible in C\#. The EagleRepair tool developed for this research is available as open source.

5G has significantly facilitated the development of attractive applications such as autonomous driving and telemedicine due to its lower latency, higher data rates, and enormous connectivity. However, there are still some security and privacy issues in 5G, such as network slicing privacy and flexibility and efficiency of network slicing selection. In the smart grid scenario, this paper proposes a 5G slice selection security scheme based on the Pohlig-Hellman algorithm, which realizes the protection of slice selection privacy data between User i(Ui) and Access and Mobility Management function (AMF), so that the data will not be exposed to third-party attackers. Compared with other schemes, the scheme proposed in this paper is simple in deployment, low in computational overhead, and simple in process, and does not require the help of PKI system. The security analysis also verifies that the scheme can accurately protect the slice selection privacy data between Ui and AMF.

An accurate state estimation (SE) considering increased uncertainty by the high penetration of renewable energy systems (RESs) is more and more important to enhance situational awareness, and the optimal and resilient operation of the renewable-rich power grids. However, it is anticipated that adversaries who plan to manipulate the target power grid will generate attacks that inject inaccurate data to the SE using the vulnerabilities of the devices and networks. Among potential attack types, false data injection attack (FDIA) is gaining popularity since this can bypass bad data detection (BDD) methods implemented in the SE systems. Although numerous FDIA detection methods have been recently proposed, the uncertainty of system configuration that arises by the continuously increasing penetration of RESs has been been given less consideration in the FDIA algorithms. To address this issue, this paper proposes a new FDIA detection scheme that is applicable to renewable energy-rich power grids. A deep learning framework is developed in particular by synergistically constructing a Bidirectional Long Short-Term Memory (Bi-LSTM) with modern smart grid characteristics. The developed framework is evaluated on the IEEE 14-bus system integrating several RESs by using several attack scenarios. A comparison of the numerical results shows that the proposed FDIA detection mechanism outperforms the existing deep learning-based approaches in a renewable energy-rich grid environment.

We continue to tackle the problem of poorly defined security metrics by building on and improving our previous work on designing sound security metrics. We reformulate the previous method into a set of conditions that are clearer and more widely applicable for deriving sound security metrics. We also modify and enhance some concepts that led to an unforeseen weakness in the previous method that was subsequently found by users, thereby eliminating this weakness from the conditions. We present examples showing how the conditions can be used to obtain sound security metrics. To demonstrate the conditions' versatility, we apply them to show that an aggregate security metric made up of sound security metrics is also sound. This is useful where the use of an aggregate measure may be preferred, to more easily understand the security of a system.

he growing trend towards network “softwarization” allows the creation and deployment of even complex network environments in a few minutes or seconds, rather than days or weeks as required by traditional methods. This revolutionary approach made it necessary to seek automatic processes to solve network security problems. One of the main issues in the automation of network security concerns the proper and efficient modeling of network traffic. In this paper, we describe two optimized Traffic Flows representation models, called Atomic Flows and Maximal Flows. In addition to the description, we have validated and evaluated the proposed models to solve two key network security problems - security verification and automatic configuration - showing the advantages and limitations of each solution.

Cybersecurity attacks, which have many business impacts, continuously become more intelligent and complex. These attacks take the form of a combination of various attack elements. APT attacks reflect this characteristic well. To defend against APT attacks, organizations should sufficiently understand these attacks based on the attack elements and their relations and actively defend against these attacks in multiple dimensions. Most organizations perform risk management to manage their information security. Generally, they use the information system risk assessment (ISRA). However, the method has difficulties supporting sufficiently analyzing security risks and actively responding to these attacks due to the limitations of asset-driven qualitative evaluation activities. In this paper, we propose a threat-driven risk assessment method. This method can evaluate how dangerous APT attacks are for an organization, analyze security risks from multiple perspectives, and support establishing an adaptive security strategy.

Recent studies have demonstrated the lack of robustness of image reconstruction networks to test-time evasion attacks, posing security risks and potential for misdiagnoses. In this paper, we evaluate how vulnerable such networks are to training-time poisoning attacks for the first time. In contrast to image classification, we find that trigger-embedded basic backdoor attacks on these models executed using heuristics lead to poor attack performance. Thus, it is non-trivial to generate backdoor attacks for image reconstruction. To tackle the problem, we propose a bi-level optimization (BLO)-based attack generation method and investigate its effectiveness on image reconstruction. We show that BLO-generated back-door attacks can yield a significant improvement over the heuristics-based attack strategy.

Vehicular Fog Computing (VFC) has been proposed to address the security and response time issues of Vehicular Ad Hoc Networks (VANETs) in latency-sensitive vehicular network environments, due to the frequent interactions that VANETs need to have with cloud servers. However, the anonymity protection mechanism in VFC may cause the attacker to launch Sybil attacks by fabricating or creating multiple pseudonyms to spread false information in the network, which poses a severe security threat to the vehicle driving. Therefore, in this paper, we summarize different types of Sybil attack detection mechanisms in VFC for the first time, and provide a comprehensive comparison of these schemes. In addition, we also summarize the possible impacts of different types of Sybil attacks on VFC. Finally, we summarize challenges and prospects of future research on Sybil attack detection mechanisms in VFC.

Advanced metamorphic malware and ransomware use techniques like obfuscation to alter their internal structure with every attack. Therefore, any signature extracted from such attack, and used to bolster endpoint defense, cannot avert subsequent attacks. Therefore, if even a single such malware intrudes even a single device of an IoT network, it will continue to infect the entire network. Scenarios where an entire network is targeted by a coordinated swarm of such malware is not beyond imagination. Therefore, the IoT era also requires Industry-4.0 grade AI-based solutions against such advanced attacks. But AI-based solutions need a large repository of data extracted from similar attacks to learn robust representations. Whereas, developing a metamorphic malware is a very complex task and requires extreme human ingenuity. Hence, there does not exist abundant metamorphic malware to train AI-based defensive solutions. Also, there is currently no system that could generate enough functionality preserving metamorphic variants of multiple malware to train AI-based defensive systems. Therefore, to this end, we design and develop a novel system, named X-Swarm. X-Swarm uses deep policy-based adversarial reinforcement learning to generate swarm of metamorphic instances of any malware by obfuscating them at the opcode level and ensuring that they could evade even capable, adversarial-attack immune endpoint defense systems.

Critical infrastructure is a key area in cybersecurity. In the U.S., it was front and center in 1997 with the report from the President’s Commission on Critical Infrastructure Protection (PCCIP), and now affects countries worldwide. Critical Infrastructure Protection must address all types of cybersecurity threats - insider threat, ransomware, supply chain risk management issues, and so on. Unsurprisingly, in the past 25 years, the risks and incidents have increased rather than decreased and appear in the news daily. As an important component of critical infrastructure protection, secure supply chain risk management must be integrated into development projects. Both areas have important implications for security requirements engineering.