Showing papers in "Computers & Security in 2020"

TL;DR: A novel ensemble convolutional neural networks (CNNs) based architecture for effective detection of both packed and unpacked malware, named Image-based Malware Classification using Ensemble of CNNs (IMCEC).

TL;DR: The results highlight the significance of enhanced input generation for dynamic analysis as DL-Droid with the state-based input generation is shown to outperform the existing state-of-the-art approaches.

TL;DR: A systematic literature review of blockchain approaches designed for EHR systems focusing only on the security and privacy aspects is performed, prior to investigating the (potential) applications of blockchain in E HR systems.

TL;DR: The results suggested that the proposed Feed-Forward Deep Neural Network (FFDNN) wireless IDS system using a Wrapper Based Feature Extraction Unit (WFEU) has greater detection accuracy than other approaches.

TL;DR: This work presents “PrivySharing,” a blockchain-based innovative framework for privacy-preserving and secure IoT data sharing in a smart city environment that conforms to some of the significant requirements outlined in the European Union General Data Protection Regulation.

TL;DR: This paper designed and developed a new feature selection algorithm named Corracc based on CorrACC, which is based on wrapper technique to filter the features and select effective feature for a particular ML classifier by using ACC metric.

TL;DR: The experimental results show that the proposed AE-IDS (Auto-Encoder Intrusion Detection System) is superior to traditional machine learning based intrusion detection methods in terms of easy training, strong adaptability, and high detection accuracy.

TL;DR: The results indicate that the most common formalization technique is theorem proving, which is most often used to verify security properties relating to smart contracts, while other techniques such as symbolic execution and model checking were also frequently used.

TL;DR: Suggestions and recommendations are described as to how the findings can be applied to mitigate cyberbullying.

TL;DR: This study develops a taxonomy for cyber range systems and evaluates the current literature focusing on architecture and scenarios, but including also capabilities, roles, tools and evaluation criteria.

TL;DR: This paper combined sequential feature selection with MLP to select the optimal features during the training phase and designed a feedback mechanism to reconstruct the detector when perceiving considerable detection errors dynamically.

TL;DR: Various types of potential SCADA vulnerabilities are described by taking real incidents reported in standard vulnerability databases and a comprehensive review of each type of vulnerability has been discussed along with recommendations for the improved SCADA security systems.

TL;DR: A byte-level malware classification method based on markov images and deep learning referred to as MDMC is proposed, which shows that MDMC has better performance than GDMC.

TL;DR: This work discusses the major works, from industry and academia towards the development of the secure ICSs, especially applicability of the machine learning techniques for the ICS cyber-security and may help to address the challenges of securing industrial processes, particularly while migrating them to the cloud environments.

TL;DR: How the research reflects the evolutionary growth of security attacks with its future prophesy, based upon the past developments in the area of computer security is discussed.

TL;DR: The use of word embedding is introduced to understand the contextual relationship that exists between API functions in malware call sequences and a prediction methodology that predicts whether an API call sequence is malicious or not from the initial API calling functions is proposed.

TL;DR: The study shows that the deep learning approaches which are used in the past few years, although still require further research, have shown great results and can be used as a preliminary plan and a roadmap for researchers interested in EEG biometric.

TL;DR: This work proposes a dynamic game framework to model a long-term interaction between a stealthy attacker and a proactive defender and proposes an iterative algorithm to compute the perfect Bayesian Nash equilibrium and uses the Tennessee Eastman process as a benchmark case study.

TL;DR: A modified Two-hidden-layered Extreme Learning Machine (TELM) is built, which uses the dependency of malware sequence elements in addition to having the advantage of avoiding backpropagation when training neural networks, to speed up the training and detection steps of malware hunting.

TL;DR: A blockchain-based privacy-preserving scheme is proposed, which realizes secure sharing of medical data between several entities involved patients, research institutions and semi-trusted cloud servers and achieves the data availability and consistency between patients and research institutions.

TL;DR: A new packet parser architecture called Blockchain-enabled Packet Parser (BPP) based on the security characteristics of the blockchain and support for data processing functions with the description of Programming Protocol-Independent Packet Processors (P4) language that has the BPP-independent attribute of the protocol is proposed.

TL;DR: It was shown that while organisational culture and security culture were correlated with ISA, security culture played an important mediating relationship between organisational Culture and ISA and suggests that organisations should focus on security culture rather than organisationalculture to improve ISA.

TL;DR: A unified model combining Multiscale Convolutional Neural Network with Long Short-Term Memory (MSCNN-LSTM) with better accuracy, false alarm rate and false negative rate is proposed.

TL;DR: This paper proposes an IDS named SwiftIDS, which is capable of both analyzing massive traffic data in high-speed networks timely and keeping satisfactory detection performance, and takes advantage of LightGBM’s effective detection performance to simplify the data preprocessing.

TL;DR: The major achievement is the description and analysis of existing feature extraction methodologies and detailed overview of datasets used in APT detection related literature, showing that the large enterprise network use case, has incorporated a much more frequent use of datasets with quite short periods of time.

TL;DR: This paper presents a meta-analyses of the distributed denial-of-service (DDoS) attacks in the context of a distributed system and some of the techniques used to attack these systems have been developed.

TL;DR: A novel and highly reliable deep learning framework, named AMalNet, to learn multiple embedding representations for Android malware detection and family attribution, and introduces a version of Graph Convolutional Networks for modeling high-level graphical semantics.

TL;DR: HYDRA is presented, a novel framework to address the task of malware detection and classification by combining various types of features to discover the relationships between distinct modalities and achieves comparable results to gradient boosting methods in the literature and higher yield in comparison with deep learning approaches.

TL;DR: This paper proposes to use one-class classification to enhance Twitter bot detection, as this allows detecting novel bot accounts, and requires only from examples of legitimate accounts, without requiring previous information about them.

TL;DR: This work uses the smart contracts and zero-knowledge proof (ZKP) algorithms to improve the existing claim identity model in blockchain to realize the identity unlinkability, effectively avoiding the exposure of the ownership of attributes.