Fortifying Your Defenses: Techniques to Thwart Adversarial Attacks and Boost Performance of Machine Learning-Based Intrusion Detection Systems

Machine learning has seen significant advancements in recent years and has proven to be highly effective in a wide range of applications, including intrusion detection systems (IDS). However, while working in adversarial environments, machine learning-based systems are known to be vulnerable to a range of attacks. In this talk, we will discuss techniques aimed at strengthening machine learning-based IDS. On the one hand, we explore techniques for enhancing the performance and robustness of IDS in adversarial environments, where we propose a contrastive learning-based approach that builds highly differentiating IDS. On the other hand, we develop efficient security mechanisms to thwart common attacks, including an adversarial example (AE) detector that filters out suspicious inputs at the model testing time, and a robust model evaluation method that leverages latent space representations to build resiliency in model aggregation against model poisoning attacks in federated learning. This talk will report our research results along this line of research.
Wenjing Lou
Virginia Tech, United States of America

Wenjing Lou is the W. C. English Endowed Professor of Computer Science at Virginia Tech and a Fellow of the IEEE. She holds a Ph.D. in Electrical and Computer Engineering from the University of Florida. Her research interests cover many topics in the cybersecurity field, with her current research interest focusing on wireless networks, blockchain systems, trustworthy machine learning systems, and security and privacy problems in the Internet of Things (IoT) systems. Prof. Lou is a highly cited researcher by the Web of Science Group. She received the Virginia Tech Alumni Award for Research Excellence in 2018, the highest university-level faculty research award. She received the INFOCOM Test-of-Time paper award in 2020. She is the TPC chair for IEEE INFOCOM 2019 and ACM WiSec 2020. She was the Steering Committee Chair for IEEE CNS conference from 2013 to 2020. She is currently a steering committee member of IEEE INFOCOM and IEEE CNS. She served as a program director at US National Science Foundation (NSF) from 2014 to 2017.

Secure Wireless Agile Networks (SWAN): Novel ML Applications in IoT Intrusion Detection and Secure RF Design

There is growing evidence that wireless networks are vulnerable to over-the-air attacks, with adversary motives ranging from extortion to state subversion. The UKRI Prosperity Partnership in Secure Wireless Agile Networks (SWAN) aims to identify, highlight, and mitigate against vulnerabilities in the Radio Frequency (RF) Open Attack Surface. Bringing together expertise in wireless communications and RF cyber security from the University of Bristol, Toshiba, Roke, and GCHQ, the Partnership aims to deliver a co-created research programme with real-world applications of national importance. Within SWAN’s programme of research, we have been able to develop several novel methods of machine learning (ML) and apply these to the detection and mitigation of potential RF cyber intrusions and to the design of secure RF architectures. This presentation will explore a number of these novel methods and highlight how ML can be utilised in the creation of resilient wireless networks for use in critical infrastructure.
Mark Beach
University of Bristol, United Kingdom

Professor Mark Beach (CEng, MIET, SMIEE) has over 35 years of experience in physical layer wireless research including spread spectrum; adaptive and smart antennas for capacity and range extension in wireless networks; MIMO aided connectivity for through-put and spectrum efficiency enhancement; millimetre wave technology, as well as secure, robust and frequency agile radio frequency technologies. He leads the delivery of the UKRI/EPSRC SWAN Prosperity Partnership in Secure Wireless Agile Networks, Expert Panel Member to DCMS on 6G, is a Co-Director of CDT in Communications, and also the School Research Impact Director. Mark is a co-founder of the Cambridge based company, ForeFrontRF, creating frequency agile technology to replace fixed frequency SAW and BAR components commonplace in cellular phone technology.