Biblio

Speech recognition technology has been applied to all aspects of our daily life, but it faces many security issues. One of the major threats is the adversarial audio examples, which may tamper the recognition results of the acoustic speech recognition system (ASR). In this paper, we propose an adversarial detection framework to detect adversarial audio examples. The method is based on the transformer self-attention mechanism. Spectrogram features are extracted from the audio and divided into patches. Position information are embedded and then fed into transformer encoder. Experimental results show that the method achieves good performance with the detection accuracy of above 96.5% under the white-box attacks and blackbox attacks, and noisy circumstances. Even when detecting adversarial examples generated by the unknown attacks, it also achieves satisfactory results.

As one of the defensive solutions against cyberattacks, an Intrusion Detection System (IDS) plays an important role in observing the network state and alerting suspicious actions that can break down the system. There are many attempts of adopting Machine Learning (ML) in IDS to achieve high performance in intrusion detection. However, all of them necessitate a large amount of labeled data. In addition, labeling attack data is a time-consuming and expensive human-labor operation, it makes existing ML methods difficult to deploy in a new system or yields lower results due to a lack of labels on pre-trained data. To address these issues, we propose a semi-supervised IDS model that leverages Generative Adversarial Networks (GANs) and Adversarial AutoEncoder (AAE), called a semi-supervised adversarial autoencoder (SAAE). Our SAAE experimental results on two public datasets for benchmarking ML-based IDS, including NF-CSE-CIC-IDS2018 and NF-UNSW-NB15, demonstrate the effectiveness of AAE and GAN in case of using only a small number of labeled data. In particular, our approach outperforms other ML methods with the highest detection rates in spite of the scarcity of labeled data for model training, even with only 1% labeled data.

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.

The security of manycore systems has become increasingly critical. In system-on-chips (SoCs), Hardware Trojans (HTs) manipulate the functionalities of the routing components to saturate the on-chip network, degrade performance, and result in the leakage of sensitive data. Existing HT detection techniques, including runtime monitoring and state-of-the-art learning-based methods, are unable to timely and accurately identify the implanted HTs, due to the increasingly dynamic and complex nature of on-chip communication behaviors. We propose AGAPE, a novel Generative Adversarial Network (GAN)-based anomaly detection and mitigation method against HTs for secured on-chip communication. AGAPE learns the distribution of the multivariate time series of a number of NoC attributes captured by on-chip sensors under both HT-free and HT-infected working conditions. The proposed GAN can learn the potential latent interactions among different runtime attributes concurrently, accurately distinguish abnormal attacked situations from normal SoC behaviors, and identify the type and location of the implanted HTs. Using the detection results, we apply the most suitable protection techniques to each type of detected HTs instead of simply isolating the entire HT-infected router, with the aim to mitigate security threats as well as reducing performance loss. Simulation results show that AGAPE enhances the HT detection accuracy by 19%, reduces network latency and power consumption by 39% and 30%, respectively, as compared to state-of-the-art security designs.

In this short paper, we survey some work at the intersection of Artificial Intelligence (AI) and security that are based on game theoretic considerations, and particularly focus on the author's (our) contribution in these areas. One half of this paper focuses on applications of game theoretic and learning reasoning for addressing security applications such as in public safety and wildlife conservation. In the second half, we present recent work that attacks the learning components of these works, leading to sub-optimal defense allocation. We finally end by pointing to issues and potential research problems that can arise due to data quality in the real world.

Blockchain and artificial intelligence are two technologies that, when combined, have the ability to help each other realize their full potential. Blockchains can guarantee the accessibility and consistent admittance to integrity safeguarded big data indexes from numerous areas, allowing AI systems to learn more effectively and thoroughly. Similarly, artificial intelligence (AI) can be used to offer new consensus processes, and hence new methods of engaging with Blockchains. When it comes to sensitive data, such as corporate, healthcare, and financial data, various security and privacy problems arise that must be properly evaluated. Interaction with Blockchains is vulnerable to data credibility checks, transactional data leakages, data protection rules compliance, on-chain data privacy, and malicious smart contracts. To solve these issues, new security and privacy-preserving technologies are being developed. AI-based blockchain data processing, either based on AI or used to defend AI-based blockchain data processing, is emerging to simplify the integration of these two cutting-edge technologies.

The recent 5G networks aim to provide higher speed, lower latency, and greater capacity; therefore, compared to the previous mobile networks, more advanced and intelligent network security is essential for 5G networks. To detect unknown and evolving 5G network intrusions, this paper presents an artificial intelligence (AI)-based network threat detection system to perform data labeling, data filtering, data preprocessing, and data learning for 5G network flow and security event data. The performance evaluations are first conducted on two well-known datasets-NSL-KDD and CICIDS 2017; then, the practical testing of proposed system is performed in 5G industrial IoT environments. To demonstrate detection against network threats in real 5G environments, this study utilizes the 5G model factory, which is downscaled to a real smart factory that comprises a number of 5G industrial IoT-based devices.

Over the past two decades, several forms of non-intrusive technology have been deployed in cooperation with medical specialists in order to aid patients diagnosed with some form of mental, cognitive or psychological condition. Along with the availability and accessibility to applications offered by mobile devices, as well as the advancements in the field of Artificial Intelligence applications and Natural Language Processing, Conversational Agents have been developed with the objective of aiding medical specialists detecting those conditions in their early stages and monitoring their symptoms and effects on the cognitive state of the patient, as well as supporting the patient in their effort of mitigating those symptoms. Coupled with the recent advances in the the scientific field of machine and deep learning, we aim to explore the grade of applicability of such technologies into cognitive health support Conversational Agents, and their impact on the acceptability of such applications bytheir end users. Therefore, we conduct a systematic literature review, following a transparent and thorough process in order to search and analyze the bibliography of the past five years, focused on the implementation of Conversational Agents, supported by Artificial Intelligence technologies and in service of patients diagnosed with Mild Cognitive Impairment and its variants.

In the operation of information technology (IT) services, operators monitor the equipment-issued alarms, to locate the cause of a failure and take action. Alarms generate simultaneously from multiple devices with physical/logical connections. Therefore, if the time and location of the alarms are close to each other, it can be judged that the alarms are likely to be caused by the same event. In this paper, we propose a method that takes a novel approach by correlating alarms considering event units using a Bayesian network based on alarm generation time, generation place, and alarm type. The topology information becomes a critical decision element when doing the alarm correlation. However, errors may occur when topology information updates manually during failures or construction. Therefore, we show that event-by-event correlation with 100% accuracy is possible even if the topology information is 25% wrong by taking into location information other than topology information.

The aim of this paper is to examine noteworthy cyberattacks that have taken place against ICS and SCADA systems and to analyse them. This paper also proposes a new classification scheme based on the severity of the attack. Since the information revolution, computers and associated technologies have impacted almost all aspects of daily life, and this is especially true of the industrial sector where one of the leading trends is that of automation. This widespread proliferation of computers and computer networks has also made it easier for malicious actors to gain access to these systems and networks and carry out harmful activities.

A direct access (DAX) file system maximizes the benefit of persistent memory(PM)’s low latency through removing the page cache layer from the file system access paths. However, this paper reveals that data block allocation of the DAX file systems in common is significantly slower than that of conventional file systems because the DAX file systems require the zero-out operation for the newly allocated blocks to prevent the leakage of old data previously stored in the allocated data blocks. The retarded block allocation significantly affects the file write performance. In addition to this revelation, this paper proposes an off-critical-path data block sanitization scheme tailored for DAX file systems. The proposed scheme detaches the zero-out operation from the latency-critical I/O path and performs that of released data blocks in the background. The proposed scheme’s design principle is universally applicable to most DAX file systems. For evaluation, we implemented our approach in Ext4-DAX and XFS-DAX. Our evaluation showed that the proposed scheme reduces the append write latency by 36.8%, and improved the performance of FileBench’s fileserver workload by 30.4%, YCSB’s workload A on RocksDB by 3.3%, and the Redis-benchmark by 7.4% on average, respectively.

In recent years, generative adversarial networks (GAN) have become a research hotspot in the field of deep learning. Researchers apply them to the field of anomaly detection and are committed to effectively and accurately identifying abnormal images in practical applications. In anomaly detection, traditional supervised learning algorithms have limitations in training with a large number of known labeled samples. Therefore, the anomaly detection model of unsupervised learning GAN is the research object for discussion and research. Firstly, the basic principles of GAN are introduced. Secondly, several typical GAN-based anomaly detection models are sorted out in detail. Then by comparing the similarities and differences of each derivative model, discuss and summarize their respective advantages, limitations and application scenarios. Finally, the problems and challenges faced by GAN in anomaly detection are discussed, and future research directions are prospected.

This article analyzes the analysis of the joint data security architecture that integrates artificial intelligence and cloud computing in the era of big data. The article discusses and analyzes the integrated applications of big data, artificial intelligence and cloud computing. As an important part of big data security protection, joint data security Protecting the technical architecture is not only related to the security of joint data in the big data era, but also has an important impact on the overall development of the data era. Based on this, the thesis takes the big data security and joint data security protection technical architecture as the research content, and through a simple explanation of big data security, it then conducts detailed research on the big data security and joint data security protection technical architecture from five aspects and thinking.

{Health diseases have been issued seriously harmful in human life due to different dehydrated food and disturbance of working environment in the organization. Precise prediction and diagnosis of disease become a more serious and challenging task for primary deterrence, recognition, and treatment. Thus, based on the above challenges, we proposed the Medical Things (MT) and machine learning models to solve the healthcare problems with appropriate services in disease supervising, forecast, and diagnosis. We developed a prediction framework with machine learning approaches to get different categories of classification for predicted disease. The framework is designed by the fuzzy model with a decision tree to lessen the data complexity. We considered heart disease for experiments and experimental evaluation determined the prediction for categories of classification. The number of decision trees (M) with samples (MS), leaf node (ML), and learning rate (I) is determined as MS=20

In the prevailing situation, the sports like economic, industrial, cultural, social, and governmental activities are carried out in the online world. Today's international is particularly dependent on the wireless era and protective these statistics from cyber-assaults is a hard hassle. The reason for cyber-assaults is to damage thieve the credentials. In a few other cases, cyber-attacks ought to have a navy or political functions. The damages are PC viruses, facts break, DDS, and exceptional attack vectors. To this surrender, various companies use diverse answers to prevent harm because of cyberattacks. Cyber safety follows actual-time data at the modern-day-day IT data. So, far, numerous techniques have proposed with the resource of researchers around the area to prevent cyber-attacks or lessen the harm due to them. The cause of this has a look at is to survey and comprehensively evaluate the usual advances supplied around cyber safety and to analyse the traumatic situations, weaknesses, and strengths of the proposed techniques. Different sorts of attacks are taken into consideration in element. In addition, evaluation of various cyber-attacks had been finished through the platform called Kali Linux. It is predicted that the complete assessment has a have a study furnished for college students, teachers, IT, and cyber safety researchers might be beneficial.

Dynamic Host Control Protocol (DHCP) is a protocol which provides IP addresses and network configuration parameters to the hosts present in the network. This protocol is deployed in small, medium, and large size organizations which removes the burden from network administrator to manually assign network parameters to every host in the network for establishing communication. Every vendor who plans to incorporate DHCP service in its device follows the working flow defined in Request for Comments (RFC). DHCP Starvation and DHCP Flooding attack are Denial of Service (DoS) attacks to prevents provision of IP addresses by DHCP. Port Security and DHCP snooping are built-in security features which prevents these DoS attacks. However, novel techniques have been devised to bypass these security features which uses ARP and ICMP protocol to perform the attack. The purpose of this research is to analyze implementation of DHCP in multiple devices to verify the involvement of both ARP and ICMP in the address acquisition process of DHCP as per RFC and to validate the results of prior research which assumes ARP or ICMP are used by default in all of devices.

Aim: Data is secured in the cloud using Elliptic Curve Cryptography (ECC) compared with Advanced Encryption Standard (AES) with improved time efficiency. Materials and Methods: Encryption and decryption time is performed with files stored in the cloud. Protecting data with improved time efficiency is carried out using ECC where the number of samples (\textbackslashmathrmN=6) and AES (\textbackslashmathrmN=6), obtained using the G-power value of 80%. Results: Mean time of ECC is 0.1683 and RSA is 0.7517. Significant value for the proposed system is 0.643 (\textbackslashmathrmp \textgreater 0.05). Conclusion: Within the limit of study, ECC performs faster in less consumption time when compared to AES.

In order to solve the problems that may arise from the negative impact of EV charging loads on the power distribution network, it is very important to predict the distribution network variability according to EV charging loads. If appropriate facility reinforcement or system operation is made through evaluation of the impact of EV charging load, it will be possible to prevent facility failure in advance and maintain the power quality at a certain level, enabling stable network operation. By analysing the degree of change in the predicted load according to the EV load characteristics through the load prediction model, it is possible to evaluate the influence of the distribution network according to the EV linkage. This paper aims to investigate the effect of EV charging load on voltage stability, power loss, reliability index and economic loss of distribution network. For this, we transformed univariate time series of EV charging data into a multivariate time series using feature engineering techniques. Then, time series forecast models are trained based on the multivariate dataset. Finally, XAI techniques such as LIME and SHAP are applied to the models to obtain the feature importance analysis results.

Design a new generation of smart power meter components, build a smart power network, implement power meter safety protection, and complete smart power meter network security protection. The new generation of smart electric energy meters mainly complete legal measurement, safety fee control, communication, control, calculation, monitoring, etc. The smart power utilization structure network consists of the master station server, front-end processor, cryptographic machine and master station to form a master station management system. Through data collection and analysis, the establishment of intelligent energy dispatching operation, provides effective energy-saving policy algorithms and strategies, and realizes energy-smart electricity use manage. The safety protection architecture of the electric energy meter is designed from the aspects of its own safety, full-scenario application safety, and safety management. Own security protection consists of hardware security protection and software security protection. The full-scene application security protection system includes four parts: boundary security, data security, password security, and security monitoring. Security management mainly provides application security management strategies and security responsibility division strategies. The construction of the intelligent electric energy meter network system lays the foundation for network security protection.

This article is about a criterion based on credibility complex fuzzy set (CCFS) to study the prevailing substitution boxes (S-box) and learn their properties to find out their suitability in image encryption applications. Also these criterion has its own properties which is discussed in detailed and on the basis of these properties we have to find the best optimal results and decide the suitability of an S-box to image encryption applications. S-box is the only components which produces the confusion in the every block cipher in the formation of image encryption. So, for this first we have to convert the matrix having color image using the nonlinear components and also using the proposed algebraic structure of credibility complex fuzzy set to find the best S-box for image encryption based on its criterion. The analyses show that the readings of GRAY S-box is very good for image data.

The data of large-scale distributed demand-side iot devices are gradually migrated to the cloud. This cloud deployment mode makes it convenient for IoT devices to participate in the interaction between supply and demand, and at the same time exposes various vulnerabilities of IoT devices to the Internet, which can be easily accessed and manipulated by hackers to launch large-scale DDoS attacks. As an easy-to-understand supervised learning classification algorithm, KNN can obtain more accurate classification results without too many adjustment parameters, and has achieved many research achievements in the field of DDoS detection. However, in the face of high-dimensional data, this method has high operation cost, high cost and not practical. Aiming at this disadvantage, this chapter explores the potential of classical KNN algorithm in data storage structure, K-nearest neighbor search and hyperparameter optimization, and proposes an improved KNN algorithm for DDoS attack detection of demand-side IoT devices.

Promising means of detecting small UAVs are FMCW radar systems. Small UAVs with an RCS value of the order of 10−3••• 10−1m2 are characterized by a low SNR (less than 10 dB). To ensure an acceptable probability of detection in the resolution element (more than 0.9), it becomes necessary to reduce the detection threshold. However, this leads to a significant increase in the probability of false alarms (more than 10−3) and is accompanied by the appearance of a large number of false plots. The work describes an algorithm for trajectory detecting of a small UAV based on a “l/n-d” criterion using Kalman filtering in a spherical coordinate system due to FMCW radar data. Statistical analysis of algorithms based on two types of criteria “3/5-2” and “5/9-2” is performed. It is shown that the algorithms allow to achieve the probability of target trajectory detection greater than 0.9 and low probability of false detection of the target trajectory less than 10−4 with the false alarm probability in the resolution element 10−3••• 10−2•

A “tripartite and bilateral” dynamic game model was constructed to study the impact of space deterrence on the challenger's military strategy in a military conflict. Based on the signal game theory, the payment matrices and optimal strategies of the sheltering side and challenging side were analyzed. In a theoretical framework, the indicators of the effectiveness of the challenger's response to space deterrence and the influencing factors of the sheltering's space deterrence were examined. The feasibility and effective means for the challenger to respond to the space deterrent in a “tripartite and bilateral” military conflict were concluded.

Now a days there are many online social networks (OSN) which are very popular among Internet users and use this platform for finding new connections, sharing their activities and thoughts. Twitter is such social media platforms which is very popular among this users. Survey says, it has more than 310 million monthly users who are very active and post around 500+ million tweets in a day and this attracts, the spammer or cyber-criminal to misuse this platform for their malicious benefits. Product advertisement, phishing true users, pornography propagation, stealing the trending news, sharing malicious link to get the victims for making money are the common example of the activities of spammers. In Aug-2014, Twitter made public that 8.5% of its active Twitter users (monthly) that is approx. 23+ million users, who have automatically contacted their servers for regular updates. Thus for a spam free environment in twitter, it is greatly required to detect and filter these spammer from the legitimate users. Here in our research paper, effectiveness & features of twitter spam detection, various methods are summarized with their benefits and limitations are presented. [1]

The data sharing is a helpful and financial assistance provided by CC. Information substance security also rises out of it since the information is moved to some cloud workers. To ensure the sensitive and important data; different procedures are utilized to improve access manage on collective information. Here strategies, Cipher text-policyattribute based encryption (CP-ABE) might create it very helpful and safe. The conventionalCP-ABE concentrates on information privacy only; whereas client's personal security protection is a significant problem as of now. CP-ABE byhidden access (HA) strategy makes sure information privacy and ensures that client's protection isn't exposed also. Nevertheless, the vast majority of the current plans are ineffectivein correspondence overhead and calculation cost. In addition, the vast majority of thismechanism takes no thought regardingabilityauthenticationor issue of security spillescapein abilityverificationstage. To handle the issues referenced over, a security protectsCP-ABE methodby proficient influenceauthenticationis presented in this manuscript. Furthermore, its privacy keys accomplish consistent size. In the meantime, the suggestedplan accomplishes the specific safetyin decisional n-BDHE issue and decisional direct presumption. The computational outcomes affirm the benefits of introduced method.