The ever-increasing interest in and widespread diffusion of Machine Learning (ML)-based applications has driven a substantial amount of research into offensive and defensive ML. ML models can be attacked from different angles: poisoning attacks, the focus of this paper, inject maliciously crafted data points in the training set to modify the model behavior; adversarial attacks maliciously manipulate inference-time data points to fool the ML model and drive the prediction of the ML model according to the attacker’s objective. Ensemble-based techniques are among the most relevant defenses against poisoning attacks and replace the monolithic ML model with an ensemble of ML models trained on different (disjoint) subsets of the training set. They assign data points to the training sets of the models in the ensemble (routing) randomly or using a hash function, assuming that evenly distributing poisoned data points positively influences ML robustness. Our paper departs from this assumption and implements a risk-based ensemble technique where a risk management process is used to perform a smart routing of data points to the training sets. An extensive experimental evaluation demonstrates the effectiveness of the proposed approach in terms of its soundness, robustness, and performance.

The Microgrid allows for more efficient and lower-cost power provisions, and is therefore more flexible than traditional power ecosystems. However, the increasingly integrated nature of these systems into network and internet-connected IT systems also potentially makes them susceptible to cyber-attack. This paper examined different challenges related to the cyber attacks threatening wireless microgrid systems from the experimental view. Wireless communication and transmission methods are widely used for secondary control of energy re-sources. However, there are risks of cyber attacks during the communication process, such as Denial-of-Service (DoS) attacks. This paper reports the investigation of potential cyber attacks on wireless communications of microgrid systems. Furthermore, this paper evaluates the practical impacts of cybersecurity breaches targeting microgrid systems, with special attention to those in Australia. In brief, the main goal of this paper is to enhance the mitigation countermeasures for cyber attacks linked to wireless microgrid systems, thus guaranteeing reliable wireless communications within these systems.

Analyzing packet loss, whether resulting from communication challenges or malicious attacks, is vital for broadcast authentication protocols. It ensures legitimate and continuous authentication across networks. While previous studies have mainly focused on countering Denial of Service (DoS) attacks' impact on packet loss, our research introduces an innovative investigation into packet loss and develops data recovery within variant TESLA protocols. We highlight the efficacy of our proposed hybrid TLI-µTESLA protocol in maintaining continuous and robust connections among network members, while maximizing data recovery in adverse communication conditions. The study examines the unique packet structures associated with each TESLA protocol variant, emphasizing the implications of losing each type on the network performance. We also introduce modifications to variant TESLA protocols to improve data recovery and alleviate the effects of packet loss. Using Java programming language, we conducted simulation analyses that illustrate the adaptability of variant TESLA protocols in recovering lost packet keys and authenticating previously buffered packets, all while maintaining continuous and robust authentication between network members. Our findings also underscore the superiority of the hybrid TLI-µTESLA protocol in terms of packet loss performance and data recovery, alongside its robust cybersecurity features, including confidentiality, integrity, availability, and accessibility. Additionally, we demonstrated the efficiency of our proposed protocol in terms of low computational and communication requirements compared to earlier TESLA protocol variants, as outlined in previous publications.

Gait biometrics which concern with recognizing individuals by the way they walk are of a paramount importance these days. Human gait is a candidate pathway for such identification tasks since other mechanisms can be concealed. Most common methodologies rely on analyzing 2D/3D images captured by surveillance cameras. Thus, the performance of such methods depends heavily on the quality of the images and the appearance variations of individuals. In this study, we describe how gait biometrics could be used in individuals' identification using a deep feature learning and inertial measurement unit (IMU) technology. We propose a model that recognizes the biological and physical characteristics of individuals, such as gender, age, height, and weight, by examining high-level representations constructed during its learning process. The effectiveness of the proposed model has been demonstrated by a set of experiments with a new gait dataset generated using a shoe-type based on a gait analysis sensor system. The experimental results show that the proposed model can achieve better identification accuracy than existing models, while also demonstrating more stable predictive performance across different classes. This makes the proposed model a promising alternative to current image-based modeling.

The rapid integration of IoT devices into everyday decision-making processes underscores the need for continuous user authentication and data integrity checking during network communication, all while minimizing energy consumption to extend device lifespan. This paper introduces the Bio-Integrated Hybrid TESLA protocol, which is a fully symmetric and energy-efficient authentication protocol designed for resource-constrained IoT devices. Based on the Hybrid TLI-lTESLA protocol, this innovative solution prioritizes high cybersecurity levels and minimal computational requirements for continuous authentication. An innovative advancement involves eliminating the public cryptography process during the synchronization stage of TESLA protocols. Instead, biometric authentication through distorted fingerprint and EEG templates is employed, to establish a non-shared symmetric session key, utilized only once. Furthermore, neither the key nor the original biometric templates are transmitted over the network, ensuring user identity preservation and effectively resolving the key distribution challenge inherent in symmetric cryptography. By offloading intensive tasks to servers and avoiding the storage or transmission of biometric data, the proposed approach conserves IoT device energy and enhances cybersecurity. Simulation analyses and cybersecurity assessments demonstrate successful synchronization, privacy preservation, and low computational demands compared to existing protocols, making the Bio-Integrated Hybrid TESLA protocol a significant advancement in IoT authentication.

This article provides in-depth experimental studies of XAI (EXplainable Artificial Intelligence) in the IoT-Edge-Cloud continuum. Within the different available XAI frameworks, such as Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) frameworks are utilized here as they are the most suitable feature map-based, model-agnostic, posthoc frameworks that match our requirements for getting real-time prediction explanations in the healthcare domain. In order to evaluate LIME and SHAP in this continuum and to make black box AI (BBAI)-based decisions interpretable, we have considered the real-world electronic health record (EHR)-based large cloud database (which could be a very large database–VLDB) and IoMT based real-time streams as edge databases for the prediction of cardiac arrest in the real-world. We have also verified the effectiveness of automated counterfactual explanations in this context for taking remedial actions. Thus, our proposed model is capable of making significant advancements in the healthcare industry by offering conscious healthcare monitoring automation along with an AI-based self-explanatory system that serves as a personalized health assistant for individuals, paving the way for the next major upgrade in healthcare.

In the era of advancement in information technology and the smart healthcare industry 5.0, the diagnosis of human diseases is still a challenging task. The accurate prediction of human diseases, especially deadly cancer diseases in the smart healthcare industry 5.0, is of utmost importance for human wellbeing. In recent years, the global Internet of Medical Things (IoMT) industry has evolved at a dizzying pace, from a small wristwatch to a big aircraft. With this advancement in the healthcare industry, there also rises the issue of data privacy. To ensure the privacy of patients’ data and fast data transmission, federated deep extreme learning entangled with the edge computing approach is considered in this proposed intelligent system for the diagnosis of lung disease. Federated deep extreme machine learning is applied for the prediction of lung disease in the proposed intelligent system. Furthermore, to strengthen the proposed model, a fused weighted deep extreme machine learning methodology is adopted for better prediction of lung disease. The MATLAB 2020a tool is used for simulation and results. The proposed fused weighted federated deep extreme machine learning model is used for the validation of the best prediction of cancer disease in the smart healthcare industry 5.0. The result of the proposed fused weighted federated deep extreme machine learning approach achieved 97.2%, which is better than the state‐of‐the‐art published methods.

Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision/making processes and even outperforming humans in some tasks. This huge progress in terms of prediction quality does not however find a counterpart in the security of such models and corresponding predictions, where perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy. Research on poisoning attacks and defenses received increasing attention in the last decade, leading to several promising solutions aiming to increase the robustness of machine learning. Among them, ensemble-based defenses, where different models are trained on portions of the training set and their predictions are then aggregated, provide strong theoretical guarantees at the price of a linear overhead. Surprisingly, ensemble-based defenses, which do not pose any restrictions on the base model, have not been applied to increase the robustness of random forest models. The work in this paper aims to fill in this gap by designing and implementing a novel hash-based ensemble approach that protects random forest against untargeted, random poisoning attacks. An extensive experimental evaluation measures the performance of our approach against a variety of attacks, as well as its sustainability in terms of resource consumption and performance, and compares it with a traditional monolithic model based on random forest. A final discussion presents our main findings and compares our approach with existing poisoning defenses targeting random forests.

File carving is a powerful technique for both digital forensics investigations and data recovery. It offers the flexibility to recover data stored on digital media independent of the underlying file system. Thus, it can be used in the cases where we need to recover deleted files or when we have a corrupted, overwritten, or unknown file system. In this paper, we present a novel video file carving (VidCarve) framework to recover and reassemble fragmented video files into playable video files. VidCarve consists of four main components: identification and recovery, weight assignment, reassembly, and file construction. This paper focuses on the weight assignment and reassembly processes where the codec specification parameters of carved fragments were overwritten. We propose several weight assignment techniques to estimate the probability of adjacency between video fragments. Based on these weights, the reassembly algorithm recovers the video files by constructing their correct sequences. We provide experimental results for the proposed techniques of weight assignment and reassembly. We claim that the overall accuracy rate can produce forensically sound evidence and play a critical role in the process of digital evidence recovery in many criminal cases.

BACKGROUND: Recognition is an essential function of human beings. Humans easily recognize a person using various inputs such as voice, face, or gesture. In this study, we mainly focus on DL model with multi-modality which has many benefits including noise reduction. We used ResNet-50 for extracting features from dataset with 2D data. RESULTS: This study proposes a novel multimodal and multitask model, which can both identify human ID and classify the gender in single step. At the feature level, the extracted features are concatenated as the input for the identification module. Additionally, in our model design, we can change the number of modalities used in a single model. To demonstrate our model, we generate 58 virtual subjects with public ECG, face and fingerprint dataset. Through the test with noisy input, using multimodal is more robust and better than using single modality. CONCLUSIONS: This paper presents an end-to-end approach for multimodal and multitask learning. The proposed model shows robustness on the spoof attack, which can be significant for bio-authentication device. Through results in this study, we suggest a new perspective for human identification task, which performs better than in previous approaches.

An amendment to this paper has been published and can be accessed via the original article.

The Internet of Things (IoT) smart devices enable many applications, such as smart energy, traffic control, water management and environmental sensing in a smart city environment. It provides the end users (individuals and enterprises) the convenience and improved computational and communication capabilities between two devices. Yet the IoT technology is accompanied by security challenges that must be addressed in order to ensure the security and privacy of the network among multiple devices. This is done by using schemes and mechanisms which accommodate the heterogeneous nature of the IoT devices environment, and the resource-constrained nature of some of its components. There have been many efforts to develop authentication protocols such as TESLA protocol. TESLA is a source authentication protocol for the broadcast network. TESLA addresses these challenges, yet it suffers from limitations to its utility and security for IoT environments. The proposed protocol-based TESLA is designed to provide lower computation against a DoS attack. The proposed scheme is using a combination of Multilevel-μTESLA and Inf-TESLA protocols. The benefit of integration between two protocols is to reduce the delay between the sender and the receiver, allows continues authenticating of the message and increasing resistance to DoS attacks. We analysis and discuss in details out proposed protocol TLI- μTESLA.

Autonomous Mobile agents can be extremely useful in dynamic environments that require a continuous network connection. Network bandwidth reduction, protocol encapsulation, software automation and intelligence gathering can significantly affect Web Services. Integrating mobile agents with Web Services enables software adaptation to cope with a dynamic environment, automated system configuration and application requirement changes that are frequent in today''s ever fast-evolving technology. In this paper, we use a lightweight and efficient composition for mobile agents based Web services complying with Representational State Transfer (REST) principles for agent creation, migration, and control. The paper presents the overall concept and architecture of RESTful agents for web services. A security scheme is proposed for mobile agent security based on an infrastructure-less Identity Based Encryption (IBE) scheme integrated with Broadcast based Secure Mobile Agent Protocol (BROSMAP). A proof- of-concept implementation is provided.

The rapid increase of connected devices and the major advances in information and communication technologies have led to great emergence in the Internet of Things (IoT). IoT devices require software adaptation as they are in continuous transition. Multi-agent based solutions offer adaptable composition for IoT systems. Mobile agents can also be used to enable interoperability and global intelligence with smart objects in the Internet of Things. The use of agents carrying personal data and the rapid increasing number of connected IoT devices require the use of security protocols to secure the user data. Elliptic Curve Cryptography (ECC) Algorithm has emerged as an attractive and efficient public-key cryptosystem. We recommend the use of ECC in the proposed Broadcast based Secure Mobile Agent Protocol (BROSMAP) which is one of the most secure protocols that provides confidentiality, authentication, authorization, accountability, integrity and non-repudiation. We provide a methodology to improve BROSMAP to fulfill the needs of Multi-agent based IoT Systems in general. The new BROSMAP performs better than its predecessor and provides the same security requirements. We have formally verified ECC-BROSMAP using Scyther and compared it with BROSMAP in terms of execution time and computational cost. The effect of varying the key size on BROSMAP is also presented. A new ECC-based BROSMAP takes half the time of Rivest-Shamir-Adleman (RSA) 2048 BROSMAP and 4 times better than its equivalent RSA 3072 version. The computational cost was found in favor of ECC-BROSMAP which is more efficient by a factor of 561 as compared to the RSA-BROSMAP.

Mobile agents are smart programs that migrate from one platform to another to perform the user task. Mobile agents offer flexibility and performance enhancements to systems and service real-time applications. However, security in mobile agent systems is a great concern. In this paper, we propose a novel Broadcast based Secure Mobile Agent Protocol (BROSMAP) for distributed service applications that provides mutual authentication, authorization, accountability, nonrepudiation, integrity, and confidentiality. The proposed system also provides protection from man in the middle, replay, repudiation, and modification attacks. We proved the efficiency of the proposed protocol through formal verification with Scyther verification tool.

Vehicular ad hoc networks (VANET) are emerging as a prominent form of mobile ad hoc networks (MANETs) and as an effective technology for providing a wide range of safety applications for vehicle passengers. Nowadays, VANETs are of an increasing importance as they enable accessing a large variety of ubiquitous services. Such increase is also associated with a similar increase in vulnerabilities in these inter-vehicular services and communications, and consequently, the number of security attacks and threats. It is of paramount importance to ensure VANETs security as their deployment in the future must not compromise the safety and privacy of their users. The successful defending against such VANETs attacks prerequisite deploying efficient and reliable security solutions and services, and the research in this field is still immature and is continuously and rapidly growing. As such, this paper is devoted to provide a structured and comprehensive overview of the recent research advances on VANETS security services, surveying the state-of-the-art on security threats, vulnerabilities and security services, while focusing on important aspects that are not well-surveyed in the literature such as VANET security assessment tools.

In this paper, a novel performance analysis of the multi-access multiple-input multiple-output relay reference-modulated differential chaos shift keying cooperative diversity (RM-DCSK-CD) is presented. New closed-form expressions for the average bit error rates are derived for multiple relaying protocols. The carried analysis is based on a novel approximation of the bit error rates of RM-DCSK systems that directly applies for high- efficiency DCSK (HE-DCSK). The analysis assumes Additive White Generalized Gaussian Noise (AWGGN) model, which includes many other noise models as special cases, and Nakagami-m fading (and hence the Rayleigh fading). Numerical results prove the accuracy of our derived expressions.

Voice over Internet protocol is the ability of transmitting voice using the Internet protocol. This paper addresses an introduction to VoIP, threats of VoIP and studies previous works of secure VoIP. We also propose practical implementations for securing VoIP by using Java and Android. Finally we give security analysis of our implementation and analyze different protocols involved in making VoIP more secure by preventing from Man in the Middle attack by using a new MIKEY protocol.

This paper focuses on one of the future applications and services area of mobile communications. Mobile devices like mobile phones and PDAs would very soon allow us to interact with other smart devices around us, thus supporting a ubiquitous society. There would be many competitive service providers selling location-based services to users. To avail such services, a user's mobile device may need to handle many service providers. It should also he able to identify and securely communicate with only genuine service providers. But these tasks could create a huge burden on the low-computing and resource-poor mobile device. Our protocol establishes a convincing trust model through which secure key distribution is accomplished. Secure job delegation and use of cost-effective cryptographic techniques help in reducing the communication and computational burden on the mobile device. The protocol also provides user privacy protection, replay protection, entity authentication, and message authentication, integrity and confidentiality.