Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self-attention-based methods perform poorly on *long-range* tasks. These tasks require correlating information that occurred "far" away from the current event, either spatially (higher-order node information) or along the time dimension (events occurred in the past). To address long-range dependencies, we introduce Continuous-Time Graph Anti-Symmetric Network (CTAN). Grounded within the ordinary differential equations framework, our method is designed for efficient propagation of information. In this paper, we show how CTAN's (i) long-range modeling capabilities are substantiated by theoretical findings and how (ii) its empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods. Our results motivate CTAN's ability to propagate long-range information in C-TDGs as well as the inclusion of long-range tasks as part of temporal graph models evaluation.

Graph Neural Networks (GNNs) are well-suited for learning on homophilous graphs, i.e., graphs in which edges tend to connect nodes of the same type. Yet, achievement of consistent GNN performance on heterophilous graphs remains an open research problem. Recent works have proposed extensions to standard GNN architectures to improve performance on heterophilous graphs, trading off model simplicity for prediction accuracy. However, these models fail to capture basic graph properties, such as neighborhood label distribution, which are fundamental for learning. In this work, we propose GCN for Heterophily (GCNH), a simple yet effective GNN architecture applicable to both heterophilous and homophilous scenarios. GCNH learns and combines separate representations for a node and its neighbors, using one learned importance coefficient per layer to balance the contributions of center nodes and neighborhoods. We conduct extensive experiments on eight real-world graphs and a set of synthetic graphs with varying degrees of heterophily to demonstrate how the design choices for GCNH lead to a sizable improvement over a vanilla GCN. Moreover, GCNH outperforms state-of-the-art models of much higher complexity on four out of eight benchmarks, while producing comparable results on the remaining datasets. Finally, we discuss and analyze the lower complexity of GCNH, which results in fewer trainable parameters and faster training times than other methods, and show how GCNH mitigates the oversmoothing problem.

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.

Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global reasoning of (scaled) dot-product attention can be the source of a major vulnerability when confronted with adversarial patch attacks. We provide a theoretical understanding of this vulnerability and relate it to an adversary's ability to misdirect the attention of all queries to a single key token under the control of the adversarial patch. We propose novel adversarial objectives for crafting adversarial patches which target this vulnerability explicitly. We show the effectiveness of the proposed patch attacks on popular image classification (ViTs and DeiTs) and object detection models (DETR). We find that adversarial patches occupying 0.5% of the input can lead to robust accuracies as low as 0% for ViT on ImageNet, and reduce the mAP of DETR on MS COCO to less than 3%.

In this paper, we describe how the electronic rolling shutter in CMOS image sensors can be exploited using a bright, modulated light source (e.g., an inexpensive, off-the-shelf laser), to inject fine-grained image disruptions. We demonstrate the attack on seven different CMOS cameras, ranging from cheap IoT to semi-professional surveillance cameras, to highlight the wide applicability of the rolling shutter attack. We model the fundamental factors affecting a rolling shutter attack in an uncontrolled setting. We then perform an exhaustive evaluation of the attack’s effect on the task of object detection, investigating the effect of attack parameters. We validate our model against empirical data collected on two separate cameras, showing that by simply using information from the camera’s datasheet the adversary can accurately predict the injected distortion size and optimize their attack accordingly. We find that an adversary can hide up to 75% of objects perceived by state-of-the-art detectors by selecting appropriate attack parameters. We also investigate the stealthiness of the attack in comparison to a naïve camera blinding attack, showing that common image distortion metrics can not detect the attack presence. Therefore, we present a new, accurate and lightweight enhancement to the backbone network of an object detector to recognize rolling shutter attacks. Overall, our results indicate that rolling shutter attacks can substantially reduce the performance and reliability of vision-based intelligent systems.

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.

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.

Both authentication and deauthentication are instrumental for preventing unauthorized access to computers and other resources. While there are obvious motivating factors for using strong authentication mechanisms, convincing users to deauthenticate is not straight-forward, since deauthentication is not considered mandatory. A user who leaves a logged-in workstation unattended (especially for a short time) is typically not inconvenienced in any way; in fact, the other way around - no annoying reauthentication is needed upon return. However, an unattended workstation is trivially susceptible to the well-known "lunchtime attack" by any nearby adversary who simply takes over the departed user's log-in session. At the same time, since deauthentication does not intrinsically require user secrets, it can, in principle, be made unobtrusive. To this end, this paper designs the first automatic user deauthentication system - FADEWICH - that does not rely on biometric-or behavior-based techniques (e.g., keystroke dynamics) and does not require users to carry any devices. It uses physical properties of wireless signals and the effect of human bodies on their propagation. To assess FADEWICH's feasibility and performance, extensive experiments were conducted with its prototype. Results show that it suffices to have nine inexpensive wireless sensors deployed in a shared office setting to correctly deauthenticate all users within six seconds (90% within four seconds) after they leave their workstation's vicinity. We considered two realistic scenarios where the adversary attempts to subvert FADEWICH and showed that lunchtime attacks fail.