Call for Papers: Empowering Future Generation of Malware Detection through Machine Learning
Keeping up with the growth of malware in today's world is becoming increasingly difficult. It is critical to build smart malware detection systems that effectively identify harmful files from real-world data sets to maintain the unexpected pattern in malware evolution. Because of technological advancements’ options, malware attacks keep growing vertically (in terms of quantity) and horizontally (in terms of varieties and capabilities). Social media, cellphones, IoT devices, and other technologies enable the production of complex malware. The complex nature and number of daily malware have necessitated machine learning (ML) approaches for dynamic file and data processing.
ML techniques can understand from real-time data, and certain machine learning neural network algorithms are qualified to assess the data and draw their detecting patterns. Considering facing a huge number of unexpected threats each day, that could be quite useful. ML principles based on dynamic and behavioural analysis approaches are possible for such a new type of malware. ML has prompted a drastic transformation in numerous sectors, notably cybersecurity, over the previous decade. Cybersecurity analysts think that AI-powered malware detection technologies will aid in the detection of emerging malware threats and enhance monitoring algorithms. Machine Learning-Malware identification modules determine whether it is a vulnerability based on the information they have acquired about an entity. Each cybersecurity application needs a malware recognition module that is effective, reliable, and expandable. For detecting attacks, a variety of ML techniques have been deployed. Support Vector Machines (SVMs), Random Forests (RFs), and Decision Trees (DTs) are examples of unsupervised and supervised approaches, as well as deep learning Artificial Neural Networks (ANNs) and certain other meta-heuristic methodologies.
ML algorithms must be trained to examine data patterns and form inferences to detect anomaly-based cyber risks. When faced with a high number of samples, the system will be unable to discriminate among safe and malicious files if, indeed, the dataset is corrupted or incorrectly classified, resulting in erroneous results. Developers must still intervene to fine-tune the algorithms to avoid producing inaccurate results. Among the most challenging components of any Machine Learning challenge is collecting suitable practice datasets. Work on assessing the influence of malware on privacy and trust in the context of cyberattacks and on addressing the challenges and proposing solutions by assisting Machine Learning on Malware Detection is especially welcomed.
Suggested research and application topics of interest include (but are not limited to):
- Exploring the Machine Learning Techniques for Mobile Malware
- New Paradigms for Supervised and Unsupervised Learning Techniques
- Combining Edge computing and Machine Learning for Detection Systems
- Novel Architectures of Deep Learning-based Malware Detection
- Meeting the Security Challenges by ML and AI Technology
- New Directions in Machine Learning for Side-Channel Attacks Setting the Future of Federated Learning and their Security and Privacy
- Machine Learning Models for Healthcare Applications
- Computational Approaches for Automated Malware Detection
- A Systematic Analysis of Industrial Malware Detection System
- Emerging Trends and Technologies for Effective Malware Detection
- Risk Management in Malware Detection Applications
Dr Dilbag Singh, Gwangju Institute of Science and Technology, South Korea
Dr Robertas Damaševičius, Silesian University of Technology, Poland
Dr Vijay Kumar, National Institute of Technology, India
First notification – 1 July 2022
Revised papers – 1 September 2022
Submission deadline – 25 November 2022
Final notification – 1 January 2023
For authorsSubmit manuscript
Working on a manuscript?
Avoid the most common mistakes and prepare your manuscript for journal editors.Learn more