Biblio

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.

With the ever increasing threat of malware, extensive research effort has been put on applying Deep Learning for malware classification tasks. Graph Neural Networks (GNNs) that process malware as Control Flow Graphs (CFGs) have shown great promise for malware classification. However, these models are viewed as black-boxes, which makes it hard to validate and identify malicious patterns. To that end, we propose CFG-Explainer, a deep learning based model for interpreting GNN-oriented malware classification results. CFGExplainer identifies a subgraph of the malware CFG that contributes most towards classification and provides insight into importance of the nodes (i.e., basic blocks) within it. To the best of our knowledge, CFGExplainer is the first work that explains GNN-based mal-ware classification. We compared CFGExplainer against three explainers, namely GNNExplainer, SubgraphX and PGExplainer, and showed that CFGExplainer is able to identify top equisized subgraphs with higher classification accuracy than the other three models.

With the dramatic increase in malicious software, the sophistication and innovation of malware have increased over the years. In particular, the dynamic analysis based on the deep neural network has shown high accuracy in malware detection. However, most of the existing methods only employ the raw API sequence feature, which cannot accurately reflect the actual behavior of malicious programs in detail. The relationship between API calls is critical for detecting suspicious behavior. Therefore, this paper proposes a malware detection method based on the graph neural network. We first connect the API sequences executed by different processes to build a directed process graph. Then, we apply Bert to encode the API sequences of each process into node embedding, which facilitates the semantic execution information inside the processes. Finally, we employ GCN to mine the deep semantic information based on the directed process graph and node embedding. In addition to presenting the design, we have implemented and evaluated our method on 10,000 malware and 10,000 benign software datasets. The results show that the precision and recall of our detection model reach 97.84% and 97.83%, verifying the effectiveness of our proposed method.

Using the methods of literature and interview, this paper analyzes the current situation of performance evaluation of volunteers in large-scale games based on mobile Internet, By analyzing the popularity of mobile Internet, the convenience of performance evaluation, the security and privacy of performance evaluation, this paper demonstrates the necessity of performance evaluation of volunteers in large-scale games based on mobile Internet, This paper puts forward the Countermeasures of performance evaluation of volunteers in large-scale games based on mobile Internet.

The introduction of the study primarily emphasises the significance of utilising block chain technologies with the possibility of privacy and security benefits from the 5G Network. One may state that the study’s primary focus is on all the advantages of adopting block chain technology to safeguard everyone’s access to crucial data by utilizing intelligent contracts to enhance the 5G network security model on information security operations.Our literature evaluation for the study focuses primarily on the advantages advantages of utilizing block chain technology advance data security and privacy, as well as their development and growth. The whole study paper has covered both the benefits and drawbacks of employing the block chain technology. The literature study part of this research article has, on the contrary hand, also studied several approaches and tactics for using the blockchain technology facilities. To fully understand the circumstances in this specific case, a poll was undertaken. It was possible for the researchers to get some real-world data in this specific situation by conducting a survey with 51 randomly selected participants.

Artificial intelligence creation comes into fashion and has brought unprecedented challenges to intellectual property law. In order to study the viewpoints of AI creation copyright ownership from professionals in different institutions, taking the papers of AI creation on CNKI from 2016 to 2021, we applied orthogonal design and analysis of variance method to construct the dataset. A kernel-SVM classifier with different kernel methods in addition to some shallow machine learning classifiers are selected in analyzing and predicting the copyright ownership of AI creation. Support vector machine (svm) is widely used in statistics and the performance of SVM method is closely related to the choice of the kernel function. SVM with RBF kernel surpasses the other seven kernel-SVM classifiers and five shallow classifier, although the accuracy provided by all of them was not satisfactory. Various performance metrics such as accuracy, F1-score are used to evaluate the performance of KSVM and other classifiers. The purpose of this study is to explore the overall viewpoints of AI creation copyright ownership, investigate the influence of different features on the final copyright ownership and predict the most likely viewpoint in the future. And it will encourage investors, researchers and promote intellectual property protection in China.

Due to its decentralized trust mechanism, blockchain is increasingly used as a trust intermediary for multi-party cooperation to reduce the cost and risk of maintaining centralized trust nowadays. And as the requirements for privacy and high throughput, consortium blockchain is widely used in data sharing and business cooperation in practical application scenarios. Nowadays, the protection of traditional medicine has been regarded as human intangible cultural heritage in recent years, but this kind of protection still faces the problem that traditional medicine prescriptions are unsuitable for disclosure and difficult to protect. Hyperledger is a consortium blockchain featuring authorized access, high throughput, and tamper-resistance, making it ideal for privacy protection and information depository in traditional medicine protection. This study proposes a solution for intellectual property protection of traditional medicine by using a blockchain platform to record prescription iterations and clinical trial data. The privacy and confidentiality of Hyperledger can keep intellectual property information safe and private. In addition, the author proposes to invite the Patent Offices and legal institutions to join the blockchain network, maintain users' properties and issue certificates, which can provide a legal basis for rights protection when infringement occurs. Finally, the researchers have built a system corresponding to the scheme and tested the system. The test outcomes of the system can explain the usability of the system. And through the test of system throughput, under low system configuration, it can reach about 200 query operations per second, which can meet the application requirements of relevant organizations and governments.

Frame deletion forensics has been a major area of video forensics in recent years. The detection effect of current deep neural network-based methods outperforms previous traditional detection methods. Recently, researchers have used residual features as input to the network to detect frame deletion and have achieved promising results. We propose an IReF (Improved Residual Feature) by analyzing the effect of residual features on frame deletion traces. IReF preserves the main motion features and edge information by denoising and enhancing the residual features, making it easier for the network to identify the tampered features. And the sparse noise reduction reduces the storage requirement. Experiments show that under the 2D convolutional neural network, the accuracy of IReF compared with residual features is increased by 3.81 %, and the storage space requirement is reduced by 78%. In the 3D convolutional neural network with video clips as feature input, the accuracy of IReF features is increased by 5.63%, and the inference efficiency is increased by 18%.

WhatsApp is one of the rare applications that has managed to become one of the most popular instant messaging applications all over the world. While inherently designed for simple and fast communication, privacy features such as end-to-end encryption have made confidential communication easy for criminals aiming to commit illegal acts. However, as it meets many daily communication and communication needs, it has a great potential to be digital evidence in interpersonal disputes. In this study, in parallel with the potential of WhatsApp application to contain digital evidence, the abuse of this situation and the manipulation method of multimedia files, which may cause wrong decisions by the judicial authorities, are discussed. The dangerous side of this method, which makes the analysis difficult, is that it can be applied by anyone without the need for high-level root authority or any other application on these devices. In addition, it is difficult to detect as no changes can be made in the database during the analysis phase. In this study, a controlled experimental environment was prepared on the example scenario, the manipulation was carried out and the prepared system analysis was included. The results obtained showed that the evidence at the forensic analysis stage is open to misinterpretation.

As an important branch of computer forensics, network forensics technology, whether abroad or at home, is in its infancy. It mainly focuses on the research on the framework of some forensics systems or some local problems, and has not formed a systematic theory, method and system. In order to improve the network forensics sys-tem, have a relatively stable and correct model for refer-ence, ensure the authenticity and credibility of network fo-rensics from the forensics steps, provide professional and non professional personnel with a standard to measure the availability of computer network crime investigation, guide the current network forensics process, and promote the gradual maturity of network forensics theories and methods, This paper presents a fuzzy decision tree reason-ing method for network forensics analysis.

Common Vulnerabilities and Exposures (CVE) databases contain information about vulnerabilities of software products and source code. If individual elements of CVE descriptions can be extracted and structured, then the data can be used to search and analyze CVE descriptions. Herein we propose a method to label each element in CVE descriptions by applying Named Entity Recognition (NER). For NER, we used BERT, a transformer-based natural language processing model. Using NER with machine learning can label information from CVE descriptions even if there are some distortions in the data. An experiment involving manually prepared label information for 1000 CVE descriptions shows that the labeling accuracy of the proposed method is about 0.81 for precision and about 0.89 for recall. In addition, we devise a way to train the data by dividing it into labels. Our proposed method can be used to label each element automatically from CVE descriptions.

Physical layer (PHY) security in decode-and-forward (DF) relay systems is discussed. Based on the types of wiretap links, the secrecy performance of three typical secure DF relay models is analyzed. Different from conventional works in this field, rigorous derivations of the secrecy channel capacity are provided from an information-theoretic perspective. Meanwhile, closed-form expressions are derived to characterize the secrecy outage probability (SOP). For the sake of unveiling more system insights, asymptotic analyses are performed on the SOP for a sufficiently large signal-to-noise ratio (SNR). The analytical results are validated by computer simulations and are in excellent agreement.

This paper deals with how to implement a system that extends insider threat behavior data using private blockchain technology to overcome the limitations of insider threat datasets. Currently, insider threat data is completely undetectable in existing datasets for new methods of insider threat due to the lack of insider threat scenarios and abstracted event behavior. Also, depending on the size of the company, it was difficult to secure a sample of data with the limit of a small number of leaks among many general users in other organizations. In this study, we consider insiders who pose a threat to all businesses as public enemies. In addition, we proposed a system that can use a private blockchain to expand insider threat behavior data between network participants in real-time to ensure reliability and transparency.

Big Data is a concept used in various sectors today, including the government sector in the Smart Government initiative. With a large amount of structured and unstructured data being managed, information assurance becomes important in adopting Big Data. However, so far, no research has focused on information assurance for Big Data. This paper identified information assurance factors for Big Data. This research used the systematic snapshot mapping approach to examine factors relating to information assurance from the literature related to Big Data from 2011 through 2021. The data extraction process in gathering 15 relevant papers. The findings revealed ten factors influencing the information assurance implementation for Big Data, with the security factor becoming the most concentrated factor with 18 sub-factors. The findings are expected to serve as a foundation for adopting information assurance for Big Data to develop an information assurance framework for Smart Government.

Machine tool is known as the mother of industry. CNC machine tool is the embodiment of modern automatic control productivity. In the context of the rapid development of the industrial Internet, a large number of equipment and systems are interconnected through the industrial Internet, realizing the flexible adaptation from the supply side to the demand side. As the a typical core system of industrial Internet, CNC system is facing the threat of industrial virus and network attack. The problem of information security is becoming more and more prominent. This paper analyzes the security risks of the existing CNC system from the aspects of terminal security, data security and network security. By comprehensively using the technologies of data encryption, identity authentication, digital signature, access control, secure communication and key management, this paper puts forward a targeted security protection and management scheme, which effectively strengthens the overall security protection ability.

With the introduction of the national “carbon peaking and carbon neutrality” strategic goals and the accelerated construction of the new generation of power systems, cloud applications built on advanced IT technologies play an increasingly important role in meeting the needs of digital power business. In view of the characteristics of the current power industrial control system operation support cloud platform with wide coverage, large amount of log data, and low analysis intelligence, this paper proposes a cloud platform network security behavior audit method based on FP-Growth association rule algorithm, aiming at the uniqueness of the operating data of the cloud platform that directly interacts with the isolated system environment of power industrial control system. By using the association rule algorithm to associate and classify user behaviors, our scheme formulates abnormal behavior judgment standards, establishes an automated audit strategy knowledge base, and improves the security audit efficiency of power industrial control system operation support cloud platform. The intelligent level of log data analysis enables effective discovery, traceability and management of internal personnel operational risks.

The fourth industrial revolution has led to the rapid development of industrial control systems. While the large number of industrial system devices connected to the Internet provides convenience for production management, it also exposes industrial control systems to more attack surfaces. Under the influence of multiple attack surfaces, sensitive data leakage has a more serious and time-spanning negative impact on industrial production systems. How to quickly locate the source of information leakage plays a crucial role in reducing the loss from the attack, so there are new requirements for tracing sensitive data in industrial control information systems. In this paper, we propose a digital watermarking traceability scheme for sensitive data in industrial control systems to address the above problems. In this scheme, we enhance the granularity of traceability by classifying sensitive data types of industrial control systems into text, image and video data with differentiated processing, and achieve accurate positioning of data sources by combining technologies such as national secret asymmetric encryption and hash message authentication codes, and mitigate the impact of mainstream watermarking technologies such as obfuscation attacks and copy attacks on sensitive data. It also mitigates the attacks against the watermarking traceability such as obfuscation attacks and copy attacks. At the same time, this scheme designs a data flow watermark monitoring module on the post-node of the data source to monitor the unauthorized sensitive data access behavior caused by other attacks.

Metaverse opens up a new social networking paradigm where people can experience a real interactive feeling without physical space constraints. Social interactions are gradually evolving from text combined with pictures and videos to 3-dimensional virtual reality, making the social experience increasingly physical, implying that more metaverse applications with immersive experiences will be developed in the future. However, the increasing data dimensionality and volume for new metaverse applications present a significant challenge in data acquisition, security, and sharing. Furthermore, metaverse applications require high capacity and ultrareliability for the wireless system to guarantee the quality of user experience, which cannot be addressed in the current fifth-generation system. Therefore, reaching the metaverse is dependent on the revolution in the sixth-generation (6G) wireless communication, which is expected to provide low-latency, high-throughput, and secure services. This article provides a comprehensive view of metaverse applications and investigates the fundamental technologies for the 6G toward metaverse.

This Innovative Practice Work-in-Progress paper presents a virtual, proactive, and collaborative learning paradigm that can engage learners with different backgrounds and enable effective retention and transfer of the multidisciplinary AI-cybersecurity knowledge. While progress has been made to better understand the trustworthiness and security of artificial intelligence (AI) techniques, little has been done to translate this knowledge to education and training. There is a critical need to foster a qualified cybersecurity workforce that understands the usefulness, limitations, and best practices of AI technologies in the cybersecurity domain. To address this import issue, in our proposed learning paradigm, we leverage multidisciplinary expertise in cybersecurity, AI, and statistics to systematically investigate two cohesive research and education goals. First, we develop an immersive learning environment that motivates the students to explore AI/machine learning (ML) development in the context of real-world cybersecurity scenarios by constructing learning models with tangible objects. Second, we design a proactive education paradigm with the use of hackathon activities based on game-based learning, lifelong learning, and social constructivism. The proposed paradigm will benefit a wide range of learners, especially underrepresented students. It will also help the general public understand the security implications of AI. In this paper, we describe our proposed learning paradigm and present our current progress of this ongoing research work. In the current stage, we focus on the first research and education goal and have been leveraging cost-effective Minecraft platform to develop an immersive learning environment where the learners are able to investigate the insights of the emerging AI/ML concepts by constructing related learning modules via interacting with tangible AI/ML building blocks.

Anomaly detection for devices (e.g, sensors and actuators) plays a crucial role in Industrial Control Systems (ICS) for security protection. The typical framework of deep learning-based anomaly detection includes a model to predict or reconstruct the state of devices and a detection mechanism to determine anomalies. The majority of anomaly detection methods use a fixed threshold detection mechanism to detect anomalous points. However, the anomalies caused by cyberattacks in ICSs are usually continuous anomaly segments. In this paper, we propose a novel detection mechanism to detect continuous anomaly segments. Its core idea is to determine the start and end times of anomalies based on the continuity characteristics of anomalies and the dynamics of error. We conducted experiments on the two real-world datasets for performance evaluation using five baselines. The F1 score increased by 3.8% on average in the SWAT dataset and increased by 15.6% in the WADI dataset. The results show a significant improvement in the performance of baselines using an error neighborhood-based continuity detection mechanism in a real-time manner.

Digital identity management system is the securi-ty infrastructure of computer and internet applications. However, currently, most of the digital identity management systems are faced with problems such as the difficulty of cross-domain authentication and interoperation, the lack of credibility of identity authentication, the weakness of the security of identity data. Although the advantages of block-chain technology have attached the attentions of experts and scholars in the field of digital identity management and many digital identity management systems based on block-chain have been built, the systems still can't completely solve the problems mentioned above. Therefore, in this pa-per, an effective digital identity management system model is proposed which combines technologies of self-sovereign identity and oracle with blockchain so as to pave a way in solving the problems mentioned above and constructing a secure and reliable digital identity management system.

With the rapid popularity of the network, the development of information encryption technology has a significant role and significance in securing network security. The security of information has become an issue of concern to the whole society, and the study of cryptography has been increasingly concerned, and the hash function is the core of modern cryptography, the most common hash algorithms are MD5 series of algorithms, SHA series of algorithms. MD5 is a popular and excellent typical Hash encryption technology today, which is used for password management, electronic signature, spam screening. In this paper, we focus on the improved MD5 algorithm with more efficiency, focusing on the internal structure of MD5, and finally making it more efficient in retrieval.

As an emerging technology, IoT is rapidly revolutionizing the global communication network with billions of new devices deployed and connected with each other. Many of these devices collect and transfer a large amount of sensitive or mission critical data, making security a top priority. Compared to traditional Internet, IoT networks often operate in open and harsh environment, and may experience frequent delays, traffic loss and attacks; Meanwhile, IoT devices are often severally constrained in computational power, storage space, network bandwidth, and power supply, which prevent them from deploying traditional security schemes. Authentication is an important security mechanism that can be used to identify devices or users. Due to resource constrains of IoT networks, it is highly desirable for the authentication scheme to be lightweight while also being highly effective. In this paper, we developed and evaluated a hash-chain-based multi-node mutual authentication algorithm. Nodes on a network all share a common secret key and broadcast to other nodes in range. Each node may also add to the hash chain and rebroadcast, which will be used to authenticate all nodes in the network. This algorithm has a linear running time and complexity of O(n), a significant improvement from the O(nˆ2) running time and complexity of the traditional pairwise multi-node mutual authentication.

From the past few years cloud services are so popular and are being used by many people from various domains for various purposes such as data storage, e-mails, backing up data and much more. While there were many options to perform such things why did people choose cloud? The answer is clouds are more flexible, convenient, reliable and efficient. Coming to security of data over cloud, it is secure to store data over cloud rather than storing data locally as there is chance of some computer breakdown or any natural disaster may also occur. There are also many threats for data security over cloud namely data breaching, lack of access-key management and much more. As the data has been processed and being stored online for various purposes, there is a clear requirement for data security. Many organizations face various challenges while storing their data over cloud such as data leakages, account hijacking, insufficient credentials and so on. So to overcome these challenges and safeguard the data, various encryption techniques were implemented. However, even though encryption is used, the data still needs to be decrypted in order to do any type of operation. As a result, we must choose a manner in which the data can be analyzed, searched for, or used in any other way without needing to be decoded. So, the objective is to introduce a technique that goes right for the above conditions mentioned and for data security over cloud.

Speech enhancement is often applied for speech-based systems due to the proneness of speech signals to additive background noise. While speech processing-based methods are traditionally used for speech enhancement, with advancements in deep learning technologies, many efforts have been made to implement them for speech enhancement. Using deep learning, the networks learn mapping functions from noisy data to clean ones and then learn to reconstruct the clean speech signals. As a consequence, deep learning methods can reduce what is so-called musical noise that is often found in traditional speech enhancement methods. Currently, one popular deep learning architecture for speech enhancement is generative adversarial networks (GAN). However, the cross-entropy loss that is employed in GAN often causes the training to be unstable. So, in many implementations of GAN, the cross-entropy loss is replaced with the least-square loss. In this paper, to improve the training stability of GAN using cross-entropy loss, we propose to use deep regret analytic generative adversarial networks (Dragan) for speech enhancements. It is based on applying a gradient penalty on cross-entropy loss. We also employ relativistic rules to stabilize the training of GAN. Then, we applied it to the least square and Dragan losses. Our experiments suggest that the proposed method improve the quality of speech better than the least-square loss on several objective quality metrics.