Machine Learning (ML) techniques have been applied over the past two decades to improve the abilities of Intrusion Detection Systems (IDSs). Over time, several enhancements have been implemented to help the ML-based IDS models tackle the ever-evolving attack behaviors. However, recent works reveal that ML models are vulnerable to adversarial perturbations. With the increasing volumes of data passing through systems, defeating adversarial attacks has become a significant challenge. Recent research suggests that Generative Adversarial Networks (GANs) possess a good potential in creating adversarial samples and tackling them, playing well on both offense and defense teams. With a motive to improve the resistance of ML-based IDS models against a powerful white-box evasion attack technique, the Carlini-Wagner, we propose a GAN-based defensive approach and evaluate it with the CSE-CIC-IDS2018 dataset. The paper presents preliminary evaluation results and discusses the direction in which we want to continue the work.

In the modern world, Machine Learning (ML) touches our day-to-day routine in various ways. Researchers have been actively working on adding intelligence to Intrusion Detection Systems (IDSs) using ML techniques because a traditional IDS can detect known attacks but is incapable of detecting unknown attacks. Two major factors on which the efficiency of an intelligent IDS model depends are – the data and the mechanism used by the model to learn the data. This paper focuses on the contribution of data, by performing an analysis of recently published datasets, namely, UNSW-NB15, Bot-IoT, and CSE-CIC-IDS2018, employing ML algorithms including Random Forest (RF), Support Vector Machines (SVMs), Keras Deep Learning models, and XGBoost. The paper compares the performance of an ML-based IDS by training it with each of them, thereby, analyzing how the choice of a dataset impacts the performance.

The collection of transportation data is crucial to data-driven decision-making. Using artificial intelligence for such data collection efforts could save substantial time and cost and help to improve transportation safety and efficiency. This research study used YOLOv4 object detection and DeepSORT tracking models to count and classify vehicles into 13 FHWA vehicle classes from video footages from existing roadside cameras. YOLOv4 was also used to detect the presence of rumble strips from roadway images and used to create a rumble strip inventory map. The trained vehicle counting/classification model achieves a counting accuracy of ~97% at daytime and ~91% at nighttime. The rumble strip detection model has ~95% accuracy. This study demonstrates that AI model can be trained to accurately count and classify vehicles under various weather, lighting, and traffic conditions, as well as to collect transportation asset data to improve roadway safety.

The growing complexity of cyberattacks has posed significant challenges to network intrusion detection systems (IDS). Despite being equipped with sophisticated machine learning capabilities, intelligent IDSs have vulnerabilities that can be exploited by adversarial algorithms which are widely known to inject subtle perturbations into data passing through IDSs. This paper evaluates the impact of two adversarial black-box attacks - Gaussian Perturbation and Genetic Algorithm - on the performance of machine learning(ML)-based IDS model, by thoroughly investigating how these adversarial algorithms affect the integrity of data and model performance. Our research contributes to a deeper understanding of how adversarial attacks generate deceptive data and underscores the importance of developing innovative strategies to defend the defenders, i.e., IDS systems.