Malware is a blanket term for Trojan, viruses, spyware, worms, and other files that are purposely created to harm computers, mobile devices, or computer networks. Malware commonly steals, encrypts, damages, and causes a mess in these devices. The growth of malware attacks has a consequence on the growth and attractiveness of mobile features in mobile devices. Most malware research aims to probe the different methods of preventing, analysing, and detecting malware attacks. This paper aims to demonstrate an exhaustive knowledge map of the Android malware by collecting a ten (10) year dataset from the Web of Science database. A bibliometric analysis was employed for analysing articles published between 2010 and 2019. Using the keyword "malware", 5622 articles were retrieved. After scrutinising with the keywords of "Android malware", 1278 articles were then collected. This study provides an overview of the articles, productivity, research area, the Web of Science categories, authors, high-cited articles, institutions, and impact journals examining malware. Research activities are continued by placing terms in the classification of malware detection systems that outline important areas in malware research. From the analysis, it can be concluded that the highest number of publications focusing on malware studies came from the continent of Asia. Additionally, this study discusses the challenges of malware studies in the recent research studies as well as the future direction.

/pdf/towards-a-systematic-description-of-the-field-using-1rk1l1st6q.pdf

Towards a systematic description of the field using bibliometric analysis: malware evolution

A Bayesian probability model for Android malware detection

A comprehensive survey on deep learning based malware detection techniques

The rapid expansion of IoT devices and their use in business and critical infrastructure has made them vulnerable to threats from hackers and malwares. These malwares pose a serious threat to the availability and reliable operation of IoT devices and can lead to serious consequences if left unchecked. The traditional ways like antivirus for defense against malwares has been found to be ineffective in context of IoT environment. Due to the variety of IoT devices, the sheer volume of malwares released every day and low computing resources available to IoT nodes, antivirus is unable to protect these networks from malwares. This is where a Machine Learning (ML) based solution offering a promising distinction. ML based solutions can learn from historical malware datasets and then reliably flag when presented with new malware.

A Comparison Between Different Machine Learning Models for IoT Malware Detection

Internet of Things (IoT) is distressing this global with its creating implementations in various pieces of growth, for instance, medicinal services, detecting, and far off checking, and so on.
 Cell phones and apps are executing effectively to recognize the vision of the IoT. Starting later, there is a quick increase in dangers that are added, virus assaults on cell phones. What’s more, the wide abuse of the portable stage on the Internet of Things gadgets fabricates safety difficulties for instance of virus exercises. Thus, to safeguard the Internet of Things gadgets from these virus exercises, an effective Malware recognition procedure is introduced in this project. This proposed classifier is assessed with static, dynamic, and hybrid highlights. From the virus data file, these highlights are chosen to utilize the IG calculation. At that point, these chosen highlights are provided as RNN-LSTM input as the proposed classifier which groups the Malware and Benign information. Re-enactment outcome showed that RNN-LSTM gets good precision by assessing it with Hybrid highlights rather than the Static and Dynamic highlights.

Detection of malware on the internet of things and its applications depends on long short-term memory network

Deep neural network has been widely used in pattern recognition and speech processing, but its vulnerability to adversarial attacks also proverbially demonstrated. These attacks perform unstructured pixel-wise perturbation to fool the classifier, which does not affect the human visual system. The role of adversarial examples in the information security field has received increased attention across a number of disciplines in recent years. An alternative approach is “like cures like”. In this paper, we propose to utilize common noise and adaptive wiener filtering to mitigate the perturbation. Our method includes two operations: noise addition, which adds natural noise to input adversarial examples, and adaptive wiener filtering, which denoising the images in the previous step. Based on the study of the distribution of attacks, adding natural noise has an impact on adversarial examples to a certain extent and then they can be removed through adaptive wiener filter, which is an optimal estimator for the local variance of the image. The proposed improved adaptive wiener filter can automatically select the optimal window size between the given multiple alternative windows based on the features of different images. Based on lots of experiments, the result demonstrates that the proposed method is capable of defending against adversarial attacks, such as FGSM (Fast Gradient Sign Method), C&W, Deepfool, and JSMA (Jacobian-based Saliency Map Attack). By compared experiments, our method outperforms or is comparable to state-of-the-art methods.

https://www.mdpi.com/2079-9292/9/10/1634/pdf

Adaptive Wiener Filter and Natural Noise to Eliminate Adversarial Perturbation

In the past decade, artificial intelligence and Internet of things (IoT) technology have been rapid development, gradually began to integrate with each other, especially in coming 5G era. Admittedly, image recognition is the key technology due to a huge number of video cameras integrated in intelligent IoT equipment, such as driverless cars. However, the rapidly growing body of research in adversarial machine learning has demonstrated that the deep learning architectures are vulnerable to adversarial examples. Thus, the raises questions about the security of intelligent Internet of thing (IoT) and trust sensitive areas. This emphasizes the urgent need for practical defense technology that can be deployed to real-time combat attacks at any time. Well-crafted small perturbations lead to the misclassification of legitimate images by neural networks, but not the human visual system. It is worth noting that many attack strategies are designed to disrupt image pixels in a visually imperceptible manner. Therefore, we propose a new defense method and take full advantage of 5G high-speed bandwidth and mobile edge computing (MEC) effectively. We use singular value decomposition (SVD) which is the optimal approximation of matrix in the sense of square loss to eliminate the perturbation. We have conducted extensive and large-scale experiments with German Traffic Sign Recognition Benchmark (GTSRB) datasets and the results show that adversarial attacks, such as Carlini-Wagner’s l2, Deepfool, and I-FSGM, can be better eliminated by the method and provide lower latency.

/pdf/defense-against-adversarial-attacks-in-traffic-sign-images-4ve6s7a9mn.pdf

Defense against adversarial attacks in traffic sign images identification based on 5G

At present, many Internet of Things services are monitored and controlled by smart phone applications. The combination of Internet of Things and smart phones provides users with many convenient services. However, these convenient services also have potential security problems, such as privacy leakage or remote intrusion. Attackers are extending the scope of attacks from existing PC and Internet environments to mobile devices. In this paper, we extract the characteristics of the network traffic generated during the Internet connection, then use the information gain algorithm to select the discriminant classification features, establish the classifier by Bayesian model updating method which is an improved algorithm based on Bayesian theory, and compare with other machine learning classifiers such as k-nearest neighbor (KNN), SVM and J48, improved algorithm has good performance on validity, accuracy, efficiency and strong practicability.

Bayesian Model Updating Method Based Android Malware Detection for IoT Services

CFIO: A conflict-free I/O mechanism to fully exploit internal parallelism for Open-Channel SSDs

The Non-Volatile Memory Express (NVMe) SSD provides high I/O performance for current computer systems, and direct memory access (DMA) is the critical enabling mechanism for direct I/O. However, the lengthy I/O stack becomes a new bottleneck that degrades the potential of NVMe SSD. This paper reveals that existing user-level DMA introduces additional overhead for pinning memory used by DMA from the user space. Moreover, it cannot adapt to I/O requests of different data sizes. This paper proposes an efficient and dynamically adaptive user-level DMA (uDMA) mechanism that can adapt to I/O requests for different data sizes and lighten the I/O software stack by amortizing per-request latency. The critical component of uDMA is the pinned memory pool, which avoids frequently pinning new memory blocks by reusing allocated and pinned memory blocks. In addition, it effectively connects the discrete pinned memory blocks by the scatter/gather lists, improving the utilization of the pinned memory pool. Compared with the latest user-level DMA method, uDMA has an improvement of at least 17% under various data sizes.

/pdf/udma-an-efficient-user-level-dma-for-nvme-ssds-29qojwyj.pdf

Jinbin Zhu

Papers

Adaptive Wiener Filter and Natural Noise to Eliminate Adversarial Perturbation

Defense against adversarial attacks in traffic sign images identification based on 5G

Bayesian Model Updating Method Based Android Malware Detection for IoT Services

CFIO: A conflict-free I/O mechanism to fully exploit internal parallelism for Open-Channel SSDs

uDMA: An Efficient User-Level DMA for NVMe SSDs