Betalogger: Smartphone Sensor-based Side-channel Attack Detection and Text Inference Using Language Modeling and Dense MultiLayer Neural Network

Javed, Abdul Rehman; Rehman, Saif Ur; Khan, Mohammad Shoaib; Alazab, Mamoun; Khan, Habib Ullah

doi:10.1145/3460392

Cited by 22 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model is compared with state of art methods like AlphaLogger 32 and Dense Multi-layer Neural Network (DMNN) 33 1. Figure 11 represents the comparison of various methods using performance matrix.…”

Section: Comparison With State Of Art Methodsmentioning

confidence: 99%

“…In order to draw attention to the problem of smartphone users' privacy being compromised by hardware sensors (accelerometer, magnetometer, and gyroscope), Javed et al 33 have proposed BetaLogger, an Android application. With a dense multi‐layer neural network (DMNN) and Language Modeling, BetaLogger effectively infers the entered text long or short on a smartphone keyboard.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

Maheswari,

Krishnamurthy

2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Side‐channel analysis (SCA) is a type of cryptanalytic attack that uses unintended ‘side‐channel’ leakage through the real‐world execution of the cryptographic algorithm to crack a secret key of an embedded system. These side‐channel errors can be discovered through tracking the energy usage of the device performing the technique, electromagnetic radiations while the encryption process, execution time, cache hits/misses, and others. Nowadays, deep learning‐based detection techniques are considered as emerging techniques that have been proposed for attack detection. Deep learning architectures have the ability to learn autonomously and concentrate on difficult features, in contrast to machine learning models. In light of these factors, the work's motive is thought to be the proposal of a deep learning‐based attack detection method. Many methods are used to decrease these assaults, however, the majority of them are inefficient and time‐demanding. In order to address these challenges, this study employs a novel deep learning‐based methodology. Pre‐processing, feature extraction, and SCA classification are the three stages of the approach proposed in this work. First, pre‐processing is used to remove unnecessary information and improve the quality of the input using data cleaning and min‐max normalization. The previously processed data are then fed as input into the proposed hybrid deep learning architecture. A Deep Residual Capsule Auto‐Encoder (DR_CAE) model is introduced in the proposed study. The deep residual neural network‐50 (DRNN‐50) is utilized to extract relevant features in this case, while the side channel analysis is done by using capsule auto‐encoder (CAE). The parameters of the proposed model are adjusted using the modified white shark optimization (MWSO) technique to improve its performance. In the results section, the proposed model is compared to various existing models in terms of accuracy, precision, recall, F‐measures, time, and so on. The proposed framework has an accuracy of 98.802%, F‐measures of 98.801%, kappa coefficient of 97.6%, the precision value of 98.81%, and recall value of 98.80%.

show abstract

Section: Comparison With State Of Art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

Maheswari,

Krishnamurthy

2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Cloud computing has enabled organizations to benefit from advanced cloud infrastructures with increased efficiency, improved work throughput, and reduced cost. In the current era, with advancements in 5G, reliable internet, smart mobile devices, IoT infrastructures, and intelligent AI-based data analytics platforms, there is a need to reevaluate how traditional cloud infrastructures are managed and address associated security issues [123,124]. With cloud-based systems, provisioning IT resources requires little knowledge of the underlying infrastructure.…”

Section: Challenges and Limitations In Cloud Computingmentioning

confidence: 99%

Cyber Security in IoT-Based Cloud Computing: A Comprehensive Survey

et al. 2021

Self Cite

View full text Add to dashboard Cite

Cloud computing provides the flexible architecture where data and resources are dispersed at various locations and are accessible from various industrial environments. Cloud computing has changed the using, storing, and sharing of resources such as data, services, and applications for industrial applications. During the last decade, industries have rapidly switched to cloud computing for having more comprehensive access, reduced cost, and increased performance. In addition, significant improvement has been observed in the internet of things (IoT) with the integration of cloud computing. However, this rapid transition into the cloud raised various security issues and concerns. Traditional security solutions are not directly applicable and sometimes ineffective for cloud-based systems. Cloud platforms’ challenges and security concerns have been addressed during the last three years, despite the successive use and proliferation of multifaceted cyber weapons. The rapid evolution of deep learning (DL) in the artificial intelligence (AI) domain has brought many benefits that can be utilized to address industrial security issues in the cloud. The findings of the proposed research include the following: we present a comprehensive survey of enabling cloud-based IoT architecture, services, configurations, and security models; the classification of cloud security concerns in IoT into four major categories (data, network and service, applications, and people-related security issues), which are discussed in detail; we identify and inspect the latest advancements in cloud-based IoT attacks; we identify, discuss, and analyze significant security issues in each category and present the limitations from a general, artificial intelligence and deep learning perspective; we provide the technological challenges identified in the literature and then identify significant research gaps in the IoT-based cloud infrastructure to highlight future research directions to blend cybersecurity in cloud.

show abstract

“…Technological advancements the world has seen during the past decade, the volume of digital media data on the internet has nearly quadrupled [1], [2]. Smartphones have enabled people to record and store every aspect of their lives in the form of multimedia files [3]- [5]. Moreover, surveillance cameras for monitoring streets, offices, and traffic for security have increased [6].…”

Section: Introductionmentioning

confidence: 99%

A Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics

et al. 2022

View full text Add to dashboard Cite

With the emergence of new digital technologies, a significant surge has been seen in the volume of multimedia data generated from various smart devices. Several challenges for data analysis have emerged to extract useful information from multimedia data. One such challenge is the early and accurate detection of anomalies in multimedia data. This study proposes an efficient technique for anomaly detection and classification of rare events in audio data. In this paper, we develop a vast audio dataset containing seven different rare events (anomalies) with 15 different background environmental settings (e.g., beach, restaurant, and train) to focus on both detection of anomalous audio and classification of rare sound (e.g., events-baby cry, gunshots, broken glasses, footsteps) events for audio forensics. The proposed approach uses the supreme feature extraction technique by extracting mel-frequency cepstral coefficients (MFCCs) features from the audio signals of the newly created dataset and selects the minimum number of best-performing features for optimum performance using principal component analysis (PCA). These features are input to state-of-theart machine learning algorithms for performance analysis. We also apply machine learning algorithms to the state-of-the-art dataset and realize good results. Experimental results reveal that the proposed approach effectively detects all anomalies and superior performance to existing approaches in all environments and cases.

show abstract

Betalogger: Smartphone Sensor-based Side-channel Attack Detection and Text Inference Using Language Modeling and Dense MultiLayer Neural Network

Cited by 22 publications

References 30 publications

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

A profiled side‐channel attack detection using deep learning model with capsule auto‐encoder network

Cyber Security in IoT-Based Cloud Computing: A Comprehensive Survey

A Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics

Contact Info

Product

Resources

About