Biblio

With the development of computer technology and information security technology, computer networks will increasingly become an important means of information exchange, permeating all areas of social life. Therefore, recognizing the vulnerabilities and potential threats of computer networks as well as various security problems that exist in reality, designing and researching computer quality architecture, and ensuring the security of network information are issues that need to be resolved urgently. The purpose of this article is to study the design and realization of information security technology and computer quality system structure. This article first summarizes the basic theory of information security technology, and then extends the core technology of information security. Combining the current status of computer quality system structure, analyzing the existing problems and deficiencies, and using information security technology to design and research the computer quality system structure on this basis. This article systematically expounds the function module data, interconnection structure and routing selection of the computer quality system structure. And use comparative method, observation method and other research methods to design and research the information security technology and computer quality system structure. Experimental research shows that when the load of the computer quality system structure studied this time is 0 or 100, the data loss rate of different lengths is 0, and the correct rate is 100, which shows extremely high feasibility.

Current sensors are widely used in power grid for power metering, automation and power equipment monitoring. Since the tradeoff between the sensitivity and the measurement range needs to be made to design a current sensor, it is difficult to deploy one sensor to measure both the small-magnitude and the large-magnitude current. In this research, we design a surface-mount current sensor by using the tunneling magneto-resistance (TMR) devices and show that the tradeoff between the sensitivity and the detection range can be broken. Two TMR devices of different sensitivity degrees were integrated into one current sensor module, and a signal processing algorithm was implemented to fusion the outputs of the two TMR devices. Then, a platform was setup to test the performance of the surface-mount current sensor. The results showed that the designed current sensor could measure the current from 2 mA to 100 A with an approximate 93 dB dynamic range. Besides, the nonintrusive feature of the surface-mount current sensor could make it convenient to be deployed on-site.

As cyber-physical systems are becoming more wide spread, it is imperative to secure these systems. In the real world these systems produce large amounts of data. However, it is generally impractical to test security techniques on operational cyber-physical systems. Thus, there exists a need to have realistic systems and data for testing security of cyber-physical systems [1]. This is often done in testbeds and cyber ranges. Most cyber ranges and testbeds focus on traditional network systems and few incorporate cyber-physical components. When they do, the cyber-physical components are often simulated. In the systems that incorporate cyber-physical components, generally only the network data is analyzed for attack detection and diagnosis. While there is some study in using physical signals to detect and diagnosis attacks, this data is not incorporated into current testbeds and cyber ranges. This study surveys currents testbeds and cyber ranges and demonstrates a prototype testbed that includes cyber-physical components and sensor data in addition to traditional cyber data monitoring.

In today's society, with the continuous development of artificial intelligence, artificial intelligence technology plays an increasingly important role in social and economic development, and hass become the fastest growing, most widely used and most influential high-tech in the world today one. However, at the same time, information technology has also brought threats to network security to the entire network world, which makes information systems also face huge and severe challenges, which will affect the stability and development of society to a certain extent. Therefore, comprehensive analysis and research on information system security is a very necessary and urgent task. Through the security assessment of the information system, we can discover the key hidden dangers and loopholes that are hidden in the information source or potentially threaten user data and confidential files, so as to effectively prevent these risks from occurring and provide effective solutions; at the same time To a certain extent, prevent virus invasion, malicious program attacks and network hackers' intrusive behaviors. This article adopts the experimental analysis method to explore how to apply the most practical, advanced and efficient artificial intelligence theory to the information system security assessment management, so as to further realize the optimal design of the information system security assessment management system, which will protect our country the information security has very important meaning and practical value. According to the research results, the function of the experimental test system is complete and available, and the security is good, which can meet the requirements of multi-user operation for security evaluation of the information system.

Misuse of caller ID spoofing combined with social engineering has the potential as a means to commit other crimes, such as fraud, theft, leaking sensitive information, spreading hoaxes, etc. The appropriate forensic technique must be carried out to support the verification and collection of evidence related to these crimes. In this research, a digital forensic analysis was carried out on the BlueStacks emulator, Redmi 5A smartphone, and SIM card which is a device belonging to the victim and attacker to carry out caller ID spoofing attacks. The forensic analysis uses the NIST SP 800-101 R1 guide and forensic tools FTK imager, Oxygen Forensic Detective, and Paraben’s E3. This research aims to determine the artifacts resulting from caller ID spoofing attacks to assist in mapping and finding digital evidence. The result of this research is a list of digital evidence findings in the form of a history of outgoing calls, incoming calls, caller ID from the source of the call, caller ID from the destination of the call, the time the call started, the time the call ended, the duration of the call, IMSI, ICCID, ADN, and TMSI.

This is the time of internet, and we are communicating our confidential data over internet in daily life. So, it is necessary to check the authenticity in communication to stop non-repudiation, of the sender. We are using the digital signature for stopping the non-repudiation. There are many versions of digital signature are available in the market. But in every algorithm, we are sending the original message and the digest message to the receiver. Hence, there is no security applied on the original message. In this paper we are proposed an algorithm which can secure the original and its integrity. In this paper we are using the RSA algorithm as the encryption and decryption algorithm, and SHA256 algorithm for making the hash.

The globalization of the integrated circuit (IC) manufacturing industry has lured the adversary to come up with numerous malicious activities in the IC supply chain. Logic locking has risen to prominence as a proactive defense strategy against such threats. CAS-Lock (proposed in CHES'20), is an advanced logic locking technique that harnesses the concept of single-point function in providing SAT-attack resiliency. It is claimed to be powerful and efficient enough in mitigating existing state-of-the-art attacks against logic locking techniques. Despite the security robustness of CAS-Lock as claimed by the authors, we expose a serious vulnerability and by exploiting the same we devise a novel attack algorithm against CAS-Lock. The proposed attack can not only reveal the correct key but also the exact AND/OR structure of the implemented CAS-Lock design along with all the key gates utilized in both the blocks of CAS-Lock. It simply relies on the externally observable Distinguishing Input Patterns (DIPs) pertaining to a carefully chosen key simulation of the locked design without the requirement of structural analysis of any kind of the locked netlist. Our attack is successful against various AND/OR cascaded-chain configurations of CAS-Lock and reports 100% success rate in recovering the correct key. It has an attack complexity of \$\textbackslashmathcalO(m)\$, where \$m\$ denotes the number of DIPs obtained for an incorrect key simulation.

Steady advancement in Artificial Intelligence (AI) development over recent years has caused AI systems to become more readily adopted across industry and military use-cases globally. As powerful as these algorithms are, there are still gaping questions regarding their security and reliability. Beyond adversarial machine learning, software supply chain vulnerabilities and model backdoor injection exploits are emerging as potential threats to the physical safety of AI reliant CPS such as autonomous vehicles. In this work in progress paper, we introduce the concept of AI supply chain vulnerabilities with a provided proof of concept autonomous exploitation framework. We investigate the viability of algorithm backdoors and software third party library dependencies for applicability into modern AI attack kill chains. We leverage an autonomous vehicle case study for demonstrating the applicability of our offensive methodologies within a realistic AI CPS operating environment.

Malware attacks in the cyber world continue to increase despite the efforts of Malware analysts to combat this problem. Recently, Malware samples have been presented as binary sequences and assembly codes. However, most researchers focus only on the raw Malware sequence in their proposed solutions, ignoring that the assembly codes may contain important details that enable rapid Malware detection. In this work, we leveraged the capabilities of deep autoencoders to investigate the presence of feature disparities in the assembly and raw binary Malware samples. First, we treated the task as outliers to investigate whether the autoencoder would identify and justify features as samples from the same family. Second, we added noise to all samples and used Deep Autoencoder to reconstruct the original samples by denoising. Experiments with the Microsoft Malware dataset showed that the byte samples' features differed from the assembly code samples.

Physical layer security is an emerging security area to tackle wireless security communications issues and complement conventional encryption-based techniques. Thus, we propose a novel scheme based on swarm intelligence optimization technique and a deep neural network (DNN) for maximizing the secrecy energy efficiency (SEE) in a cooperative relaying underlay cognitive radio- and non-orthogonal multiple access (NOMA) system with a non-linear energy harvesting user which is exposed to multiple eavesdroppers. Satisfactorily, simulation results show that the proposed particle swarm optimization (PSO)-DNN framework achieves close performance to that of the optimal solutions, with a meaningful reduction in computation complexity.

Recent advances in deep learning typically, with the introduction of transformer based models has shown massive improvement and success in many Natural Language Processing (NLP) tasks. One such area which has leveraged immensely is conversational agents or chatbots in open-ended (chit-chat conversations) and task-specific (such as medical or legal dialogue bots etc.) domains. However, in the era of automation, there is still a dearth of works focused on one of the most relevant use cases, i.e., tutoring dialog systems that can help students learn new subjects or topics of their interest. Most of the previous works in this domain are either rule based systems which require a lot of manual efforts or are based on multiple choice type factual questions. In this paper, we propose EDICA (Educational Domain Infused Conversational Agent), a language tutoring Virtual Agent (VA). EDICA employs two mechanisms in order to converse fluently with a student/user over a question and assist them to learn a language: (i) Student/Tutor Intent Classification (SIC-TIC) framework to identify the intent of the student and decide the action of the VA, respectively, in the on-going conversation and (ii) Tutor Response Generation (TRG) framework to generate domain infused and intent/action conditioned tutor responses at every step of the conversation. The VA is able to provide hints, ask questions and correct student's reply by generating an appropriate, informative and relevant tutor response. We establish the superiority of our proposed approach on various evaluation metrics over other baselines and state of the art models.

In recent years, differential privacy has gradually become a standard definition in the field of data privacy protection. Differential privacy does not need to make assumptions about the prior knowledge of privacy adversaries, so it has a more stringent effect than existing privacy protection models and definitions. This good feature has been used by researchers to solve the in-depth learning problem restricted by the problem of privacy and security, making an important breakthrough, and promoting its further large-scale application. Combining differential privacy with BEGAN, we propose the DP-BEGAN framework. The differential privacy is realized by adding carefully designed noise to the gradient of Gan model training, so as to ensure that Gan can generate unlimited synthetic data that conforms to the statistical characteristics of source data and does not disclose privacy. At the same time, it is compared with the existing methods on public datasets. The results show that under a certain privacy budget, this method can generate higher quality privacy protection data more efficiently, which can be used in a variety of data analysis tasks. The privacy loss is independent of the amount of synthetic data, so it can be applied to large datasets.

In this paper, the malicious code is run in the sandbox in a safe and controllable environment, the API sequence is deduplicated by the idea of the longest common subsequence, and the CNN and Bi-LSTM are integrated to process and analyze the API sequence. Compared with the method, the method using deep learning can have higher accuracy and work efficiency.

Accurately constructing dynamic network topology is one of the core tasks to provide on-demand security services to the ubiquitous network. Existing schemes cannot accurately construct dynamic network topologies in time. In this paper, we propose a novel scheme to construct the ubiquitous network topology. Firstly, ubiquitous network nodes are divided into three categories: terminal node, sink node, and control node. On this basis, we propose two operation primitives (i.e., addition and subtraction) and three atomic operations (i.e., intersection, union, and fusion), and design a series of algorithms to describe the network change and construct the network topology. We further use our scheme to depict the specific time-varying network topologies, including Satellite Internet and Internet of things. It demonstrates that their communication and security protection modes can be efficiently and accurately constructed on our scheme. The simulation and theoretical analysis also prove that the efficiency of our scheme, and effectively support the orchestration of protection capabilities.

Hardware IPs are assumed to be roots-of-trust in complex SoCs. However, their design and security verification are still heavily dependent on manual expertise. Extensive research in this domain has shown that even cryptographic modules may lack information flow security, making them susceptible to remote attacks. Further, when an SoC is in the hands of the attacker, physical attacks such as fault injection are possible. This paper introduces EISec, a novel tool utilizing symbolic execution for exhaustive analysis of hardware IPs. EISec operates at the pre-silicon stage on the gate level netlist of a design. It detects information flow security violations and generates the exhaustive set of control sequences that reproduces them. We further expand its capabilities to quantify the confusion and diffusion present in cryptographic modules and to analyze an FSM's susceptibility to fault injection attacks. The proposed methodology efficiently explores the complete input space of designs utilizing symbolic execution. In short, EISec is a holistic security analysis tool to help hardware designers capture security violations early on and mitigate them by reporting their triggers.

Electrical load forecasting is an essential part of the smart grid to maintain a stable and reliable grid along with helping decisions for economic planning. With the integration of more renewable energy resources, especially solar photovoltaic (PV), and transitioning into a prosumer-based grid, electrical load forecasting is deemed to play a crucial role on both regional and household levels. However, most of the existing forecasting methods can be considered black-box models due to deep digitalization enablers, such as Deep Neural Networks (DNN), where human interpretation remains limited. Additionally, the black box character of many models limits insights and applicability. In order to mitigate this shortcoming, eXplainable Artificial Intelligence (XAI) is introduced as a measure to get transparency into the model’s behavior and human interpretation. By utilizing XAI, experienced power market and system professionals can be integrated into developing the data-driven approach, even without knowing the data science domain. In this study, an electrical load forecasting model utilizing an XAI tool for a Norwegian residential building was developed and presented.

Random numbers are essential for communications security, as they are widely employed as secret keys and other critical parameters of cryptographic algorithms. The Linux random number generator (LRNG) is the most popular open-source software-based random number generator (RNG). The security of LRNG is influenced by the overall design, especially the quality of entropy sources. Therefore, it is necessary to assess and quantify the quality of the entropy sources which contribute the main randomness to RNGs. In this paper, we perform an empirical study on the quality of entropy sources in LRNG with Linux kernel 5.6, and provide the following two findings. We first analyze two important entropy sources: jiffies and cycles, and propose a method to predict jiffies by cycles with high accuracy. The results indicate that, the jiffies can be correctly predicted thus contain almost no entropy in the condition of knowing cycles. The other important finding is the failure of interrupt cycles during system boot. The lower bits of cycles caused by interrupts contain little entropy, which is contrary to our traditional cognition that lower bits have more entropy. We believe these findings are of great significance to improve the efficiency and security of the RNG design on software platforms.

In this article, we propose a generic cyber-physical framework, developed in our laboratory, for smart grid control and monitoring in real-time. Our framework is composed of four key elements: (1) system layer which embeds a physical or emulated power system network, (2) data analysis layer to execute real-time data-driven grid analysis algorithms, (3) backend layer with a generic data storage framework which supports multiple databases with functionally different architectures, and (4) visualization layer where multiple customized or commercially available user interfaces can be deployed concurrently for grid control and monitoring. These four layers are interlinked via bidirectional communication channels. Such a flexible and scalable framework provides a cohesive environment to enhance smart grid situational awareness. We demonstrate the utility of our proposed architecture with several case studies where we estimate a modified IEEE-33 bus distribution network topology entirely from synchrophasor measurements, without any prior knowledge of the grid network, and render the same on visualization platform. Three demonstrations are included with single and multiple system operators having complete and partial measurements.

The technology advance and convergence of cyber physical systems, smart sensors, short-range wireless communications, cloud computing, and smartphone apps have driven the proliferation of Internet of things (IoT) devices in smart homes and smart industry. In light of the high heterogeneity of IoT system, the prevalence of system vulnerabilities in IoT devices and applications, and the broad attack surface across the entire IoT protocol stack, a fundamental and urgent research problem of IoT security is how to effectively collect, analyze, extract, model, and visualize the massive network traffic of IoT devices for understanding what is happening to IoT devices. Towards this end, this paper develops and demonstrates an end-to-end system with three key components, i.e., the IoT network traffic monitoring system via programmable home routers, the backend IoT traffic behavior analysis system in the cloud, and the frontend IoT visualization system via smartphone apps, for monitoring, analyzing and virtualizing network traffic behavior of heterogeneous IoT devices in smart homes. The main contributions of this demonstration paper is to present a novel system with an end-to-end process of collecting, analyzing and visualizing IoT network traffic in smart homes.

DDoS attacks, one of the oldest forms of cyberthreats, continue to be a favorite tool of mass interruption, presenting cybersecurity hazards to practically every type of company, large and small. As a matter of fact, according to IDC, DDoS attacks are predicted to expand at an 18 percent compound annual growth rate (CAGR) through 2023, indicating that it is past time to enhance investment in strong mitigation systems. And while some firms may assume they are limited targets for a DDoS assault, the amount of structured internet access to power corporation services and apps exposes everyone to downtime and poor performance if the infrastructure is not protected against such attacks. We propose using correlations between missing packets to increase detection accuracy. Furthermore, to ensure that these correlations are calculated correctly.

The paper presents the design of fuzzy logic controller based unified power flow controller (UPFC) to improve power system security performance during steady state as well as fault conditions. Fuzzy interference has been design with two inputs Vref and Vm for the shunt voltage source Converter and two inputs for Series Id, Idref, Iq, Iqref at the series voltage source converter location. The coordination of shunt and series VSC has been achieved by using fuzzy logic controller (FLC). The comparative performance of PI based UPFC and fuzzy based UPFC under abnormal condition has been validated in MATLB domain. The combination of fuzzy with a UPFC is tested on multi machine system in MATLAB domain. The results shows that the power system security enhancement as well as oscillations damping.

This work expands on our prior work on an architecture and supporting protocols to efficiently integrate constrained devices into an Information-Centric Network-based Internet of Things in a way that is both secure and scalable. In this work, we propose a scheme for addressing additional threats and integrating trust-based behavioral observations and attribute-based access control by leveraging the capabilities of less constrained coordinating nodes at the network edge close to IoT devices. These coordinating devices have better insight into the behavior of their constituent devices and access to a trusted overall security management cloud service. We leverage two modules, the security manager (SM) and trust manager (TM). The former provides data confidentiality, integrity, authentication, and authorization, while the latter analyzes the nodes' behavior using a trust model factoring in a set of service and network communication attributes. The trust model allows trust to be integrated into the SM's access control policies, allowing access to resources to be restricted to trusted nodes.

The paper considers the important problem of information protection in complex energy systems. The expert assessment of information protection in complex energy systems method has been developed. Based on the conducted research and data processing, a method of forming the analytical basis for decision-making aimed at ensuring the competitiveness of complex information protection systems has been developed.

Insider threats are steadily increasing, and the damage is also enormous. To prevent insider threats, security solutions, such as DLP, SIEM, etc., are being steadily developed. However, they have limitations due to the high rate of false positives. In this paper, we propose a data analysis method and methodology for responding to a technology leak incident. The future study may be performed based on the proposed methodology.

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