Acoustic fingerprints can be used for device-to-device authentication due to manufacturing-induced variations in microphones and speakers. However, previous works have focused mostly on recognizing single devices from a set of multiple devices, which may not be sufficiently realistic since in practice, a single device has to be recognized from a very large pool of devices that are not available for training machine learning classifiers. Therefore, in this work, we focus on one-class classification algorithms, namely one-class Support Vector Machine and the local outlier factor. As such, learning the fingerprint of a single device is sufficient to recognize the legitimate device and reject all other attempts to impersonate it. The proposed application can also rely on cloud-based deployment to free the smartphone from intensive computational tasks or data storage. For the experimental part, we rely both on smartphones and an automotive-grade Android headunit, exploring in-vehicle environments as the main area of application. We create a dataset consisting of more than 5000 measurements and achieve a recognition rate ranging from 50% to 100% for different devices under various environmental conditions such as distance, altitude, and component aging. These conditions also serve as our limitations, however, we propose different solutions for overcoming them, which are part of our threat model.

The development of Intrusion Detection Systems (IDS) for in-vehicle buses has gained a lot of momentum in recent years as the number of reported vulnerabilities and the degree of interconnectivity for modern vehicles are on the rise. Since intrusion detection is resource consuming, it can be performed on computationally capable Android head units that are now present inside vehicles. Moreover, these units are connected to the internet, which enables the use of more complex algorithms that run in cloud environments. In this work we develop one such approach: an IDS that consists of a locally installed copy, running on head units, and a centralized instance of it that runs in the cloud and monitors traffic for groups of similar vehicles. Additionally, the centralized instance is part of a cloud service for intrusion detection which is continuously updated with the most recent types of attacks. The classification results of the cloud-based service are further analyzed by an incident response team which confirms the presence of known attacks, analyzes new types of attacks and assesses their impact. The output of this activity is stored on the Blockchain as ISO/SAE 21434 compliant reports, ensuring the transparency and traceability of the reported incidents.

Fingerprinting smartphones using their accelerometers has several applications, including activity recognition, driving style classification and device to device authentication. In this work, we study accelerometer-based smartphone fingerprinting. We gather data from mobile devices placed together to record identical vibrations. Then, we extract time domain features, which we use to train multiple traditional machine learning algorithms based on statistical properties of the data. Finally, we use the raw data in a more complex Convolutional Neural Network and compare the results. To make the investigations more challenging, we discuss fingerprinting both distinct and identical smartphones and reach an accuracy close to 100% with several traditional classifiers.

Automatic testing and reverse engineering of in-vehicle components have become topics of significant interest as they allow industry professionals to get a better understanding of component behaviour and attack surfaces. In this work we pursue the automatic testing of in-vehicle instrument clusters. These devices may be subject to attacks that may mislead the driver regarding the current state of the car. Understanding the feasibility of such attacks requires the ability to determine the behaviour of the cluster in response to specific instructions received from the CAN bus. For this purpose we use fuzz testing and a camera in order to remove manual intervention and set room for automatic learning of the commands that can be sent to the cluster. This enables the automatic detection of the commands with little or no human intervention. We test our framework on three clusters from real world vehicles and determine in an automatic manner a sufficiently large number of commands and responses that they trigger.

Mobile device pairing inside vehicles is a ubiquitous task which requires easy to use and secure solutions. In this work we exploit the audio-video domain for pairing devices inside vehicles. In principle, we rely on the widely used elliptical curve version of the Diffie-Hellman key-exchange protocol and extract the session keys from the acoustic domain as well as from the visual domain by using the head unit display. The need for merging the audio-visual domains first stems from the fact that in-vehicle head units generally do not have a camera so they cannot use visual data from smartphones, however, they are equipped with microphones and can use them to collect audio data. Acoustic channels are less reliable as they are more prone to errors due to environmental noise. However, this noise can be also exploited in a positive way to extract secure seeds from the environment and audio channels are harder to intercept from the outside. On the other hand, visual channels are more reliable but can be more easily spotted by outsiders, so they are more vulnerable for security applications. Fortunately, mixing these two types of channels results in a solution that is both more reliable and secure for performing a key exchange.

As car sharing becomes an increasingly common task, mediating user access rights from external servers comes with threats regarding user’s privacy. Clearly, users can be tracked by service mediators, e.g., cloud providers, that manage vehicle fleets, etc. In this work we design and test a simple solution based on oblivious transfer, a well-known and secure cryptographic block, that allows to preserve user’s privacy when gaining access to the vehicle. We test the feasibility of deploying such a solution on Android capable smartphones but also account for potential in-vehicle components, e.g., car head units, that may be soon put to such tasks. We use Microsoft Azure as cloud service provider and deploy a Java implementation, based on the Bouncy Castle cryptographic library, on the server side. Our experimental results show that Android based units are capable of handling the required cryptographic operations and the implementation of the employed protocol can be done by existing open-source support.