The International Source of Innovation for the Information Security and IT Audit Professional

Computers & Security is one of the most respected journals in IT security, being recognized worldwide as THE primary source of reference for IT security research and applications expertise.

Computers & Security provides the IT security community with a unique blend of leading edge research and sound practical management advice. It is aimed at the professional involved with computer security, audit, control and data integrity in all sectors - industry, commerce and academia - helping the community build and operate fully secure systems and organisations.

With its high-profile editorial board and informative regular features and columns, the journal is essential reading for IT security professionals around the world.

    Our cutting edge research will help you secure and maintain your systems
    We accept only the highest quality of papers ensuring that you receive the relevant and practical advice you need
    We don't only highlight the threats, we give you the solutions

Special Issue on Advances in Robust Intrusion Detection through Machine Learning
截稿日期: 2024-12-20

Intrusion detection systems are a key component in the fight against cyber attacks. Robustness by design – the ability to identify intrusions even when evasion techniques are employed – should be a core characteristic of any intrusion detection technique.

Guest editors:

Mauro Conti
Full Professor
University of Padua, Padua, Italy
conti-journal@math.unipd.it

Fabio De Gaspari
Assistant Professor
Sapienza University of Rome, Rome, Italy
degaspari@di.uniroma1.it

Jianying Zhou
Full Professor
Singapore University of Technology and Design, Singapore
jianying_zhou@sutd.edu.sg

Special issue information:

Intrusion detection systems are a key component in the fight against cyber attacks. Robustness by design – the ability to identify intrusions even when evasion techniques are employed – should be a core characteristic of any intrusion detection technique. Intrusion detection approaches, however, are often proposed and validated only against existing attacks, without considering how evolving adversaries might adapt to evade the proposed defenses. The growing adoption of machine learning and deep learning models for cyber attack detection has further exacerbated this issue. These models are often used as black-box oracles for intrusion detection, with no in-depth analysis on how detection decisions are made, or considerations for their vulnerability evasion.

The ability of cybersecurity solutions to withstand evasion and data manipulation plays a crucial role in the security of computer systems, and novel research efforts in intrusion

detection should focus on robust-by-design approaches. This special issue provides an opportunity to present advances in all areas of machine learning-based intrusion detection, such as behavioral detection, static detection, and provenance-based detection, as well as novel evasion techniques and countermeasures, with a strong emphasis on empirical and theoretical analysis of resilience to evasion and manipulation attacks.

Manuscript submission information:

Manuscript Submission Deadline *: 20/12/2024

Manuscripts should be submitted using the online submission system of the journal at https://www.editorialmanager.com/cose/default.aspx  

Authors should select article type 'VSI: Robust ML IDS' during the submission. The author guidance could be found at Guide for authors - Computers & Security - ISSN 0167-4048 | ScienceDirect.com by Elsevier

Keywords:

Intrusion detection, machine learning, robustness