Improved Testing of AI-Based Anomaly Detection Systems Using Synthetic Surveillance Data

Abstract

Major transportation surveillance protocols have not been specified with cyber security in mind and therefore provide no encryption nor identification. These issues expose air and sea transport to false data injection attacks (FDIAs), in which an attacker modifies, blocks or emits fake surveillance messages to dupe controllers and surveillance systems. There has been growing interest in conducting research on machine learning-based anomaly detection systems that address these new threats. However, significant amounts of data are needed to achieve meaningful results with this type of model. Raw, genuine data can be obtained from existing databases but need to be preprocessed before being fed to a model. Acquiring anomalous data is another challenge: such data is much too scarce for both the Automatic Dependent Surveillance–Broadcast (ADS-B) and the Automatic Identification System (AIS). Crafting anomalous data by hand, which has been the sole method applied to date, is hardly suitable for broad detection model testing. This paper proposes an approach built upon existing libraries and ideas that offers ML researchers the necessary tools to facilitate the access and processing of genuine data as well as to automatically generate synthetic anomalous surveillance data to constitute broad, elaborated test datasets. We demonstrate the usability of the approach by discussing work in progress that includes the reproduction of related work, creation of relevant datasets and design of advanced anomaly detection models for both domains of application.

Supervised ADS-B Anomaly Detection Using a False Data Generator

“…data are recorded. Note that the FDI-T software has also been used to acquire ADS-B datasets to test anomaly detection AI models in another work done in our laboratory [6]. In this work two types of attacks were considered for anomaly detection: gradual attacks and waypoints attacks.…”

“…This research as well as our previous one published in [5] are the only studies which, to the best of our knowledge, use supervised learning for ADS-B anomaly detection. Our research and [6] use the same false data injection generator (with a domain specific language) specifically devised for generating attacked ADS-B datasets contrary to anything else found in the literature. Finally we were able to detect gradual attacks on any of the previously mentioned features using a meta-model made of models trained on individual gradual attacks.…”

Trust the Crowd: Wireless Witnessing to Detect Attacks on ADS-B-Based Air-Traffic Surveillance

“…There are several open attack vectors that, from a scientific perspective, would allow attacking ADS-B on different levels. Chevrot et al [3] present a framework for arbitrary false data injection and outline detection strategies. Nevertheless, we must always consider the necessary effort for an attack and its feasibility in a real-world scenario.…”