Machine learning-based intelligent systems have experienced a massive growth over the past few years, and are close to becoming ubiquitous in the technology surrounding our daily lives. Examples of such systems are abundant -intelligent consumer appliances such as automated home security systems, intelligent voice service-enabled software assistants such as Alexa, online recommender systems for social media feeds and email spam filters, automated image and biometric data recognition software used for homeland security applications, automated controllers on self-driving vehicles, all employ machine learning based algorithms for making decisions and taking actions. Machine learning-based systems have been shown to be vulnerable to security attacks from malicious adversaries. The vulnerability of these systems is further aggravated as it is non-trivial to establish the authenticity of data used to train the system, and even innocuous perturbations to the training data can be used to manipulate the system’s behavior in unintended ways. As machine learning-based systems become pervasive in our society, it is essential to direct research towards issues related to security, trust, reliability and robustness of such systems, so that humans can use them in a safe and sustained manner. The contents of the forthcoming book will address the overarching need towards making automated, machine learning-based systems more robust and resilient against adversarial attacks.
We invite chapter contributions that address current technology trends and solutions, open issues, critical challenges and hard problems, and surveys in the area of adversarial machine learning with relevance to cybersecurity. Topics of interest include, but are not limited to the following:
· Adversary-aware Machine Learning - Reinforcement Learning, Lifelong Learning, Deep Learning
· Adversarial leaning for cybersecurity problems such as network intrusion detection, malware detection, Web spoofing, phishing, etc.
· Generative Adversarial Networks
· Adversary- aware Prediction, Forecasting and Decision Making Techniques
· Game Theory and Game Playing to counter adversarial learning
· Adversarial Issues and Techniques for Cyber-Physical Systems, Adversarial Robotics
· Operations Research related to Adversarial Learning
· Applications of Adversarial Learning
· Security Threats and Vulnerabilities from Adversarial Learning
· Human factors and adversarial learning with human-in-the-loop
December 31, 2019 – Final manuscripts due
January 15, 2020 – Final accept/reject decisions
January 31, 2020 - Final manuscripts due from authors
Second quarter of 2020: Publication
Prithviraj (Raj) Dasgupta, Joseph B. Collins, Ranjeev Mittu
Distributed Systems Section, Information Technology Division
U. S. Naval Research Laboratory, Washington D.C.
For questions and inquiries send email to: raj.dasgupta@nrl.navy.mil