In this paper, we show that by using inertial sensor data generated by a smart ring, worn on the finger, the user can be authenticated when making mobile payments or when knocking on a door (for access control). The proposed system can be deployed purely in software and does not require updates to existing payment terminals or infrastructure. We also demonstrate that smart ring data can authenticate smartwatch gestures, and vice versa, allowing either device to act as an implicit second factor for the other. To validate the system, we conduct a user study (n=21) to collect inertial sensor data from users as they perform gestures, and we evaluate the system against an active impersonation attacker. Based on this data, we develop payment and access control authentication models for which we achieve EERs of 0.04 and 0.02, respectively.

The lack of standard input interfaces in the Internet of Things (IoT) ecosystems presents a challenge in securing such infrastructures. To tackle this challenge, we introduce a novel behavioral biometric system based on naturally occurring interactions with objects in smart environments. This biometric leverages existing sensors to authenticate users without requiring any hardware modifications of existing smart home devices. The system is designed to reduce the need for phone-based authentication mechanisms, on which smart home systems currently rely. It requires the user to approve transactions on their phone only when the user cannot be authenticated with high confidence through their interactions with the smart environment. We conduct a real-world experiment that involves 13 participants in a company environment, using this experiment to also study mimicry attacks on our proposed system. We show that this system can provide seamless and unobtrusive authentication while still staying highly resistant to zero-effort, video, and in-person observation-based mimicry attacks. Even when at most 1% of the strongest type of mimicry attacks are successful, our system does not require the user to take out their phone to approve legitimate transactions in more than 80% of cases for a single interaction. This increases to 92% of transactions when interactions with more objects are considered.

In this paper, we show that the tap gesture, performed when a user 'taps' a smartwatch onto an NFC-enabled terminal to make a payment, is a biometric capable of implicitly authenticating the user and simultaneously recognising intent-to-pay. The proposed system can be deployed purely in software on the watch without requiring updates to payment terminals. It is agnostic to terminal type and position and the intent recognition portion does not require any training data from the user. To validate the system, we conduct a user study (n=16) to collect wrist motion data from users as they interact with payment terminals and to collect long-term data from a subset of them (n=9) as they perform daily activities. Based on this data, we identify optimum gesture parameters and develop authentication and intent recognition models, for which we achieve EERs of 0.08 and 0.04, respectively.

The field of touch-based authentication has been rapidly developing over the last decade, creating a fragmented and difficult-to-navigate area for researchers and application developers alike due to the variety of methods investigated. In this study, we perform a systematic literature analysis of 30 studies on the techniques used for feature extraction, classification, and aggregation in touch-based authentication systems as well as the performance metrics reported by each study. Based on our findings, we design a set of experiments to compare the performance of the most frequently used techniques in the field under clearly defined conditions. In addition, we introduce three new techniques for touch-based authentication: an expanded feature set (consisting of 149 unique features), a multi-algorithm ensemble-based classifier, and a Recurrent Neural Network based stacking aggregation method. The comparison includes 14 feature sets, 11 classifiers, and 5 aggregation methods. In total, 219 model configurations are examined and we show that our novel techniques outperform the current state-of-the-art in each category. The results are also validated across three different publicly available datasets. Finally, we discuss the findings of our investigation with the aim of making the field more understandable and accessible for researchers and practitioners.

In this article, we verify physical events using data from an ensemble of smart home sensors. This approach both protects against event sensor faults and sophisticated attackers. To validate our system’s performance, we set up a “smart home” in an office environment. We recognize 22 event types using 48 sensors over the course of two weeks. Using data from the physical sensors, we verify the event stream supplied by the event sensors to detect both masking and spoofing attacks. We consider three threat models: a zero-effort attacker, an opportunistic attacker, and a sensor-compromise attacker who can arbitrarily modify live sensor data. For spoofed events, we achieve perfect classification for 9 out of 22 events and achieve a 0% false alarm rate at a detection rate exceeding 99.9% for 15 events. For 11 events the majority of masking attacks can be detected without causing any false alarms. We also show that even a strong opportunistic attacker is inherently limited to spoofing few select events and that doing so involves lengthy waiting periods. Finally, we demonstrate the vulnerability of a single-classifier system to compromised sensor data and introduce a more secure approach based on sensor fusion.

The study aims to understand and quantify the privacy threat landscape of touch-based biometrics. Touch interactions from mobile devices are ubiquitous and do not require additional permissions to collect. Two privacy threats were examined - user tracking and personal information leakage. First, we designed a practical fingerprinting simulation experiment and executed it on a large publicly available touch interactions dataset. We found that touch-based strokes can be used to fingerprint users with high accuracy and performance can be further increased by adding only a single extra feature. The system can distinguish between new and returning users with up to 75% accuracy and match a new session to the user it originated from with up to 74% accuracy. In the second part of the study, we investigated the possibility of predicting personal information attributes through the use of touch interaction behavior. The attributes we investigated were age, gender, dominant hand, country of origin, height, and weight. We found that our model can predict the age group and gender of users with up to 66% and 62% accuracy respectively. Finally, we discuss countermeasures, limitations and provide suggestions for future work in the field.

In this paper, we present AltVoice -- a system designed to help user's protect their privacy when using remotely accessed voice services. The system allows a user to conceal their true voice identity information with no cooperation from the remote voice service: AltVoice re-synthesizes user's spoken audio to sound as if it has been spoken by a different, private identity. The system converts audio to its textual representation at its midpoint, and thus removes any linkage between the user's voice and the generated private voices. We implement AltVoice and we propose six different methods to generate private voice identities, each is based on a user-known secret. We identify the system's trade-offs, and we investigate them for each of the proposed identity generation methods. Specifically, we investigate generated voices' diversity, word error rate, perceived speech quality and the success of attackers under privacy compromise and authentication compromise attack scenarios. Our results show that AltVoice-generated voices are not easily linked to original users, enabling users to protect themselves from voice data leakages and allowing for the revocability of (generated) voice data; akin to using passwords. However the results also show further work is needed on ensuring that the produced audio is natural, and that identities of private voices are distinct from one another. We discuss the future steps into improving AltVoice and the new implications that its existence has for the creations of remotely accessed voice services.

In this paper, we show that as a user makes mobile payments with a smartwatch, the height of the user can be inferred purely from inertial sensor data captured on the watch (with R2 scores of up to 0.77). Besides unwanted information exposure, we also show that users of a similar height are more difficult to distinguish between in terms of their tap gesture data and that an attacker who chooses a victim of a similar height can improve the success chance of impersonation (by increasing the false acceptance rate by up to 20.6%).

In this paper, we investigate common pitfalls affecting the evaluation of authentication systems based on touch dynamics. We consider different factors that lead to misrepresented performance, are incompatible with stated system and threat models or impede reproducibility and comparability with previous work. Specifically, we investigate the effects of (i) small sample sizes (both number of users and recording sessions), (ii) using different phone models in training data, (iii) selecting non-contiguous training data, (iv) inserting attacker samples in training data and (v) swipe aggregation. We perform a systematic review of 30 touch dynamics papers showing that all of them overlook at least one of these pitfalls. To quantify each pitfall's effect, we design a set of experiments and collect a new longitudinal dataset of touch dynamics from 470 users over 31 days comprised of 1,166,092 unique swipes. We make this dataset and our code available online. Our results show significant percentage-point changes in reported mean EER for several pitfalls: including attacker data (2.55%), non-contiguous training data (3.8%), phone model mixing (3.2%-5.8%). We show that, in a common evaluation setting, cumulative effects of these evaluation choices result in a combined difference of 8.9% EER. We also largely observe these effects across the entire ROC curve. Furthermore, we validate the pitfalls on four distinct classifiers - SVM, Random Forest, Neural Network, and kNN. Based on these insights, we propose a set of best practices that, if followed, will lead to more realistic and comparable reporting of results in the field.

Attributing interactions with Internet of Things (IoT) devices to specific users in smart environments is extremely important as it enables personalized configurations and access control. This requirement is particularly stringent when it comes to parental control measures designed to protect children from contact with dangerous machinery or viewing materials that are inappropriate for their age. To this end, we show that naturally occurring interactions with objects in smart environments can be used as a behavioral biometric in order to identify users. The heterogeneous nature of smart devices enables the collection of a wide variety of inputs from such interactions. In addition, this system model allows for seamless identification, without the need for active user participation or rearrangement of the IoT devices.We conduct a remote study taking place in six households composed of 25 participants. We demonstrate that our system can identify users in multi-user environments with an average accuracy of at least 91% for a single object interaction without requiring any sensors on the object itself. This accuracy rises to 100% when six or more consecutive interactions are considered.

In this paper, we present our system design for conducting longitudinal daily-task studies with the same workers throughout on Amazon Mechanical Turk. We implement this system to conduct a study into touch dynamics, and present our experiences, challenges and lessons learned from doing so. Study participants installed our application on their Apple iOS phones and completed two tasks daily for 31 days. Each task involves performing a series of scrolling or swiping gestures, from which behavioral information such as movement speed or pressure is extracted. The completion of the daily tasks did not require extra interaction with the Mechanical Turk platform, yet paid workers through it. This differs somewhat from the typical rapid completion of one-off tasks that workers are used to on Amazon Mechanical Turk. This atypical use of the platform prompted us to evaluate aspects related to long-term worker retention and engagement over the study period, in particular the impacts of payment schedule (amount and structure over time) and reminder notifications. We also investigate the specific concern of reconciling informed consent with workers' desire to complete tasks quickly. We find that using the Mechanical Turk platform for conducting longitudinal daily task studies is a viable method to augment or replace traditional lab studies.

Drones are becoming increasingly popular for hobbyists and recreational use. But with this surge in popularity comes increased risk to privacy as the technology makes it easy to spy on people in otherwise-private environments, such as an individual's home. An attacker can fly a drone over fences and walls to observe the inside of a house, without having physical access. Existing drone detection systems require specialist hardware and expensive deployment efforts, making them inaccessible to the general public. In this work, we present a drone detection system that requires minimal prior configuration and uses inexpensive commercial off-the-shelf hardware to detect drones that are carrying out privacy invasion attacks. We use a model of the attack structure to derive statistical metrics for movement and proximity that are then applied to received communications between a drone and its controller. We test our system in real-world experiments with two popular consumer drone models mounting privacy invasion attacks using a range of flight patterns. We are able both to detect the presence of a drone and to identify which phase of the privacy attack was in progress while being resistant to false positives fromother mobile transmitters. For line-of-sight approaches using our kurtosis-based method, we are able to detect all drones at a distance of 6 m, with the majority of approaches detected at 25 m or farther from the target window without suffering false positives for stationary or mobile non-drone transmitters.

In this paper, we present our system design for conducting recurring daily studies on Amazon Mechanical Turk. We implement this system to conduct a study into touch dynamics, and present our experiences, challenges and lessons learned from doing so. Study participants installed our application on their Apple iOS phones and completed two tasks daily for 31 days. Each task involves performing a series of scrolling or swiping gestures, from which behavioral information such as movement speed or pressure is extracted. Taking place over a time period of 31 days, our study utilized a self-contained app which workers used to complete daily tasks without requiring extra HITs. This differs somewhat from the typical rapid completion of one-off tasks on Amazon Mechanical Turk. This atypical use of the platform prompted us to study aspects related to long-term user retention over the study period: payment schedule (amount and structure over time), regular notifications, payment satisfaction and overall satisfaction. We also investigate the specific concern of reconciling informed consent with workers' desire to complete tasks quickly. We find that using the Mechanical Turk platform in this way leads to data of comparable quality to that of lab based studies, and that our study design choices show a statistically significant effect in keeping workers engaged.

In this paper, we propose a system that enables photoplethysmogram (PPG)-based authentication by using a smartphone camera. PPG signals are obtained by recording a video from the camera as users are resting their finger on top of the camera lens. The signals can be extracted based on subtle changes in the video that are due to changes in the light reflection properties of the skin as the blood flows through the finger. We collect a dataset of PPG measurements from a set of 15 users over the course of 6-11 sessions per user using an iPhone X for the measurements. We design an authentication pipeline that leverages the uniqueness of each individual's cardiovascular system, identifying a set of distinctive features from each heartbeat. We conduct a set of experiments to evaluate the recognition performance of the PPG biometric trait, including cross-session scenarios which have been disregarded in previous work. We found that when aggregating sufficient samples for the decision we achieve an EER as low as 8%, but that the performance greatly decreases in the cross-session scenario, with an average EER of 20%.

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update procedure. We show that such attacks can be carried out even by attackers with physical limitations (no digital access to the sensor) and zero knowledge of training data (they know neither decision boundaries nor user template). Based on the adversaries' own templates, they craft several intermediate samples that incrementally bridge the distance between their own template and the legitimate user's. As these adversarial samples are added to the template, the attacker is eventually accepted alongside the legitimate user. To avoid detection, we design the attack to minimize the number of rejected samples. We design our method to cope with weak assumptions for the attacker and we evaluate the effectiveness of this approach on state-of-the-art face recognition pipelines based on deep neural networks. We find that in white-box scenarios, adversaries can successfully carry out the attack in over 70 % of cases with less than ten injection attempts. Even in black-box scenarios, we find that exploiting the transferability of adversarial samples from surrogate models can lead to successful attacks in around 15 % of cases. Finally, we design a poisoning detection technique that leverages the consistent directionality of template updates in feature space to discriminate between legitimate and malicious updates. We evaluate such a countermeasure with a set of intra-user variability factors which may present the same directionality characteristics, obtaining equal error rates for the detection between 7-14% and leading to over 99% of attacks being detected after only two sample injections. We design our method to cope with weak assumptions for the attacker and we evaluate the effectiveness of this approach on state-of-the-art face recognition pipelines based on deep neural networks. We find that in white-box scenarios, adversaries can successfully carry out the attack in over 70 % of cases with less than ten injection attempts. Even in black-box scenarios, we find that exploiting the transferability of adversarial samples from surrogate models can lead to successful attacks in around 15 % of cases. Finally, we design a poisoning detection technique that leverages the consistent directionality of template updates in feature space to discriminate between legitimate and malicious updates. We evaluate such a countermeasure with a set of intra-user variability factors which may present the same directionality characteristics, obtaining equal error rates for the detection between 7-14% and leading to over 99% of attacks being detected after only two sample injections.

With the rising availability of smart devices (e.g., smart thermostats, lights, locks, etc.), they are increasingly combined into "smart homes". A key component of smart homes are event sensors that report physical events (such as doors opening or the light turning on) which can be triggered automatically by the system or manually by the user. However, data from these sensors are not always trustworthy. Both faults in the event sensors and involvement of active attackers can lead to reporting of events that did not physically happen (event spoofing). This is particularly critical, as smart homes can trigger event chains (e.g., turning the radiator offwhen a window is opened) without involvement of the user. The goal of this paper is to verify physical events using data from an ensemble of sensors (such as accelerometers or air pressure sensors) that are commonly found in smart homes. This approach both protects against event sensor faults and sophisticated attackers. In order to validate our system's performance, we set up a "smart home" in an office environment. We recognize 22 event types using 48 sensors over the course of two weeks. Using data from the physical sensors, we verify the event stream supplied by the event sensors. We consider two threat models: a zero-effort attacker who spoofs events at arbitrary times and an opportunistic attacker who has access to alive stream of sensor data to better time their attack. We achieve perfect classification for 9 out of 22 events and achieve a 0% false alarm rate at a detection rate exceeding 99.9% for 15 events. We also show that even a strong opportunistic attacker is inherently limited to spoofing few select events and that doing so involves lengthy waiting periods.

In this work we address three overlooked practical challenges of continuous authentication systems based on eye movement biometrics: (i) changes in lighting conditions, (ii) task dependent features and the (iii) need for an accurate calibration phase. We collect eye movement data from 22 participants. To measure the effect of the three challenges, we collect data while varying the experimental conditions: users perform four different tasks, lighting conditions change over the course of the session and we collect data related to both accurate (user-specific) and inaccurate (generic) calibrations. To address changing lighting conditions, we identify the two main sources of light, i.e., screen brightness and ambient light, and we propose a pupil diameter correction mechanism based on these. We find that such mechanism can accurately adjust for the pupil shrinking or expanding in relation to the varying amount of light reaching the eye. To account for inaccurate calibrations, we augment the previously known feature set with new features based on binocular tracking, where the left and the right eye are tracked separately. We show that these features can be extremely distinctive even when using a generic calibration. We further apply a cross-task mapping function based on population data which systematically accounts for the dependency of features to tasks (e.g., reading a text and browsing a website lead to different eye movement dynamics). Using these enhancements, even while relaxing assumptions about the experimental conditions, we show that our system achieves significantly lower error rates compared to previous work. For intra-task authentication, without user-specific calibration and in variable screen brightness and ambient lighting, we achieve an equal error rate of 3.93% with only two minutes of training data. For the same setup but with constant screen brightness (e.g., as for a reading task) we can achieve equal error rates as low as of 1.88%.

Attacks on behavioral biometrics have become increasingly popular. Most research has been focused on presenting a previously obtained feature vector to the biometric sensor, often by the attacker training themselves to change their behavior to match that of the victim. However, obtaining the victim's biometric information may not be easy, especially when the user's template on the authentication device is adequately secured. As such, if the authentication device is inaccessible, the attacker may have to obtain data elsewhere. In this paper, we present an analytic framework that enables us to measure how easily features can be predicted based on data gathered in a different context (e.g., different sensor, performed task or environment). This framework is used to assess how resilient individual features or entire biometrics are against such cross-context attacks. In order to be able to compare existing biometrics with regard to this property, we perform a user study to gather biometric data from 30 participants and five biometrics (ECG, eye movements, mouse movements, touchscreen dynamics and gait) in a variety of contexts. We make this dataset publicly available online. Our results show that many attack scenarios are viable in practice as features are easily predicted from a variety of contexts. All biometrics include features that are particularly predictable (e.g., amplitude features for ECG or curvature for mouse movements). Overall, we observe that cross-context attacks on eye movements, mouse movements and touchscreen inputs are comparatively easy while ECG and gait exhibit much more chaotic cross-context changes.

In this work we present a systematic presentation attack against ECG biometrics.We demonstrate the attack's effectiveness using the Nymi Band, a wrist band that uses electrocardiography (ECG) as a biometric to authenticate the wearer.We instantiate the attack using a hardware-based Arbitrary Waveform Generator (AWG), an AWG software using a computer sound card, and the playback of ECG signals encoded as .wavfiles using an off-the-shelf audio player.In two sets of experiments we collect data from a total of 41 participants using a variety of ECG monitors, including a medical monitor, a smartphone-based mobile monitor and the Nymi Band itself.We use the first dataset to understand the statistical differences in biometric features that arise from using different measurement devices and modes.Such differences are addressed through the automated derivation of so-called mapping functions, whose purpose is to transform ECG signals from any device in order to resemble the morphology of the signals recorded with the Nymi Band.As part of our second dataset, we enroll users into the Nymi Band and test whether data from any of our sources can be used for a signal injection attack.Using data collected directly on the Nymi Band we achieve a success rate of 81%.When only using data gathered on other devices, this rate decreases to 43% when using raw data, and 62% after applying the mapping function.While we demonstrate the attack on the Nymi Band, we expect other ECG-based authentication systems to most likely suffer from the same, fundamental weaknesses.