Call for Book Chapters

Deep Learning Applications for Cyber Security

Book title: Deep Learning Applications for Cyber Security

Series title: Advanced Sciences and Technologies for Security Applications

Publisher: Springer


In the last decade, cyber security applications have increasingly relied on machine learning methods, including spam and malware detection, discovery of new malware families and Botnets, detecting software exploits, blocking phishing web pages, and preventing fraudulent financial transactions, just to name a few. With evolving cyber threat landscape, it's no longer sufficient to leverage only on traditional security solutions. These legacy solutions are built on known and identified rule sets. Signature driven security monitoring capabilities cannot scale to fully meet the demand of advanced cyber security objectives and cybercrime detection and prevention.

With recent technological advancement, machine learning methods themselves have advanced. In particular, Deep Learning techniques demonstrate significant improvements compared to “traditional” machine learning methods, and have resulted in delivering new industry standards in highly cognitive tasks, including, but not limited to, image recognition, audio classification, speech translation, natural language processing, machine translation, computer games, robots, and self-driving cars.

The Deep Learning models essentially emulate the cognitive system of human beings encoding complex knowledge into layers of neurons. The system will then selectively activate corresponding neurons when taking on specific tasks (e.g. recognising cats in images). From booming research activities to extensive media coverage, Artificial intelligence (AI) techniques are becoming future-proof skills.

Cyber security is a fast growing field demanding a great deal of attention because of remarkable progresses in social networks, cloud and web technologies, e-commerce, mobile environment, smart grid, Internet of Things (IoT), etc. With this ever-interconnected world, abundant of machine generated data have become available fostering adoption of various machine learning applications,

This book will therefore address the question of how deep learning methods can be used to advance cyber security objectives. This book attempts to fill an important gap between Deep Learning and Cyber Security communities. The proposed topics will cover a wide range of modern and practical deep learning techniques, frameworks and development tools enabling the audience to innovate with those cutting-edge research advancement in various cyber security use cases.

Suggested Topics

The proposed book bridges two popular topics: Cyber Security and Deep Learning with an emphasis on inducing potential audience to grow interests in applying Deep Learning techniques in Cyber Security applications. It aims at preparing the readers with essential Deep Learning knowledge and tools to solve practical Cyber Security use cases. The scope is limited to mature and proven techniques with ample examples for readers to digest the core knowledge. The timing is appropriate for a compilation of the cutting-edge research in this exciting and emerging field in a dedicated book.

Submissions are solicited on the following topics, but not limited to:

  • Modern Deep Learning Techniques
    • Deep NLP (natural language processing)
    • Regularization and Optimization Techniques
    • Forward and Backward Propagation
    • Effective feature embedding
    • Neural networks for graphs
    • Generative adversarial networks
    • Restricted Boltzmann Machine
    • Deep reinforcement learning
    • Relational modeling and prediction
    • Semantic knowledge-bases
    • Neural abstract machines and program induction
    • Deep learning architectures
    • Performance metrics
    • Model Selection and
    • Forward and Backward Propagations
    • Regularization and Optimization Techniques
    • Convolutional Networks
    • Recurrent Neural Networks

  • Deep Learning Framework and Tools
    • Popular Frameworks
    • Popular Tools for quick prototyping
    • Deep Learning with GPUs
    • Deep Learning in the Cloud

  • Deep Learning for Security
    • Malware identification, analysis and similarity
    • Representation and detection of social engineering attacks
    • Botnet identification and detection
    • Intrusion detection and response
    • Spam and phishing detection
    • Classification of sequences of system/network events
    • Security in social networks
    • Application of learning to computer forensics
    • Program representation
    • Learning in adversarial environments
    • Web Application
    • Security, Privacy, Trust and Safety
    • Mobile Computing, Internet of Things (IoT)
    • Cloud, Apps and Services, and their Security
    • Big Data architectures for network security
    • Detecting data and information leakage

Manuscript guidelines:

Please visit the Book Manuscript Guidelines on

Proposal Submission:

Prospective authors should submit a 2-3 page proposal.

Important Dates

1. Chapter proposals due date: May 1, 2018 (extension: 15 June 2018)

2. Notification of acceptance of proposals: May 20, 2018

3. Full chapter submission: Jul 15, 2018

4. Chapter reviews feedback due date: Aug 5, 2018 (Each chapter will be reviewed by two/three experts to ensure the quality of work)

5. Camera-ready submission of revised chapters due date: Aug 15, 2018

6. Manuscript delivery to the publisher: Sep 1, 2018

Contact Information:

Dr Mamoun Alazab (alazab.m[AT]ieee[DOT]org)

Dr MingJian Tang (mj2tang[AT]gmail[DOT]com)

Shared task on Detecting Malicious Domain names (DMD 2018):

We are very happy to announce that authors of selected papers from the Shared task on Detecting Malicious Domain names (DMD 2018) workshop will be invited to extend and improve their contributions for book chapters in the Deep Learning Applications for Cyber Security book.