Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by a particular sampler, or embed specific keys that allow the identification of the LLM user. However, simultaneously using the same embedding for both detection and user identification leads to a false detection problem, whereby, as user capacity grows, unwatermarked text is increasingly likely to be falsely detected as watermarked. Through theoretical analysis, we identify the underlying causes of this phenomenon. Building on these insights, we propose Dual Watermarking which jointly encodes detection and identification watermarks into generated text, significantly reducing false positives while maintaining high detection accuracy. Our experimental results validate our theoretical findings and demonstrate the effectiveness of our approach.
Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicious user identification, speaker anonymization methods were proposed. Current methods, particularly based on universal adversarial patch (UAP) applications, have drawbacks such as significant degradation of audio quality, decreased speech recognition quality, low transferability across different voice biometrics models, and performance dependence on the input audio length. To mitigate these drawbacks, in this work, we introduce and leverage the novel Exponential Total Variance (TV) loss function and provide experimental evidence that it positively affects UAP strength and imperceptibility. Moreover, we present a novel scalable UAP insertion procedure and demonstrate its uniformly high performance for various audio lengths.
The field of energy-free sensing and context recognition has recently gained significant attention as it allows operating systems without external power sources. Photovoltaic cells can convert light energy into electrical energy to power sensing devices, but their power may not be sufficient to ensure energy-free sensing due to the varying power needs of sensors and high computational demands. In this paper, we propose the use of photovoltaic cells as a standalone sensor for the recognition of different contexts, including user identification, step counting, and location tracking. The system utilizes the photocurrent readings generated by the photovoltaic cells to capture the unique mobility patterns of different users. By analyzing these patterns, the system can accurately identify the user, count the number of steps taken, and track the user's location. We propose a computationally efficient DTW to match the variable length sequences of photocurrent readings to a database of known patterns and identify the closest subject and location matches. The system was rigorously evaluated in a realistic environment, and the results indicate that it can accurately estimate step count, identify subjects, and localize them with an accuracy of 88%, 90%, and 43cm, respectively. This is achieved while the proposed system is non-intrusive and can operate without external power sources, making it a promising technology for energy-free sensing and context recognition.
Electrocardiogram (ECG)-based biometrics offer a promising method for user identification, combining intrinsic liveness detection with morphological uniqueness. However, elevated heart rates introduce significant physiological variability, posing challenges to pattern recognition systems and leading to a notable performance gap between resting and post-exercise conditions. Addressing this gap is critical for advancing ECG-based biometric systems for real-world applications. We propose DE-PADA, a Dual Expert model with Personalized Augmentation and Domain Adaptation, designed to enhance robustness across diverse physiological states. The model is trained primarily on resting-state data from the evaluation dataset, without direct exposure to their exercise data. To address variability, DE-PADA incorporates ECG-specific innovations, including heartbeat segmentation into the PQRS interval, known for its relative temporal consistency, and the heart rate-sensitive ST interval, enabling targeted feature extraction tailored to each region's unique characteristics. Personalized augmentation simulates subject-specific T-wave variability across heart rates using individual T-wave peak predictions to adapt augmentation ranges. Domain adaptation further improves generalization by leveraging auxiliary data from supplementary subjects used exclusively for training, including both resting and exercise conditions. Experiments on the University of Toronto ECG Database demonstrate the model's effectiveness. DE-PADA achieves relative improvements in post-exercise identification rates of 26.75% in the initial recovery phase and 11.72% in the late recovery phase, while maintaining a 98.12% identification rate in the sitting position. These results highlight DE-PADA's ability to address intra-subject variability and enhance the robustness of ECG-based biometric systems across diverse physiological states.
We present our work on leveraging low-frame-rate monochrome (blue light) videos of fingertips, captured with an off-the-shelf fingerprint capture device, to extract vital signs and identify users. These videos utilize photoplethysmography (PPG), commonly used to measure vital signs like heart rate. While prior research predominantly utilizes high-frame-rate, multi-wavelength PPG sensors (e.g., infrared, red, or RGB), our preliminary findings demonstrate that both user identification and vital sign extraction are achievable with the low-frame-rate data we collected. Preliminary results are promising, with low error rates for both heart rate estimation and user authentication. These results indicate promise for effective biometric systems. We anticipate further optimization will enhance accuracy and advance healthcare and security.
In this paper, we propose a conceptual framework for personalized brain-computer interface (BCI) applications, which can offer an enhanced user experience by customizing services to individual preferences and needs, based on endogenous electroencephalography (EEG) paradigms including motor imagery (MI), speech imagery (SI), and visual imagery. The framework includes two essential components: user identification and intention classification, which enable personalized services by identifying individual users and recognizing their intended actions through EEG signals. We validate the feasibility of our framework using a private EEG dataset collected from eight subjects, employing the ShallowConvNet architecture to decode EEG features. The experimental results demonstrate that user identification achieved an average classification accuracy of 0.995, while intention classification achieved 0.47 accuracy across all paradigms, with MI demonstrating the best performance. These findings indicate that EEG signals can effectively support personalized BCI applications, offering robust identification and reliable intention decoding, especially for MI and SI.
Resting-state EEG data in neuroscience research serve as reliable markers for user identification and reveal individual-specific traits. Despite this, the use of resting-state data in EEG classification models is limited. In this work, we propose a feature concatenation approach to enhance decoding models' generalization by integrating resting-state EEG, aiming to improve motor imagery BCI performance and develop a user-generalized model. Using feature concatenation, we combine the EEGNet model, a standard convolutional neural network for EEG signal classification, with functional connectivity measures derived from resting-state EEG data. The findings suggest that although grounded in neuroscience with data-driven learning, the concatenation approach has limited benefits for generalizing models in within-user and across-user scenarios. While an improvement in mean accuracy for within-user scenarios is observed on two datasets, concatenation doesn't benefit across-user scenarios when compared with random data concatenation. The findings indicate the necessity of further investigation on the model interpretability and the effect of random data concatenation on model robustness.
Leveraging perception from radar data can assist multiple communication tasks, especially in highly-mobile and large-scale MIMO systems. One particular challenge, however, is how to distinguish the communication user (object) from the other mobile objects in the sensing scene. This paper formulates this \textit{user identification} problem and develops two solutions, a baseline model-based solution that maps the objects angles from the radar scene to communication beams and a scalable deep learning solution that is agnostic to the number of candidate objects. Using the DeepSense 6G dataset, which have real-world measurements, the developed deep learning approach achieves more than $93.4\%$ communication user identification accuracy, highlighting a promising path for enabling integrated radar-communication applications in the real world.
With the widespread of digital environments, reliable authentication and continuous access control has become crucial. It can minimize cyber attacks and prevent frauds, specially those associated with identity theft. A particular interest lies on keystroke dynamics (KD), which refers to the task of recognizing individuals' identity based on their unique typing style. In this work, we propose the use of pre-trained language models (PLMs) to recognize such patterns. Although PLMs have shown high performance on multiple NLP benchmarks, the use of these models on specific tasks requires customization. BERT and RoBERTa, for instance, rely on subword tokenization, and they cannot be directly applied to KD, which requires temporal-character information to recognize users. Recent character-aware PLMs are able to process both subwords and character-level information and can be an alternative solution. Notwithstanding, they are still not suitable to be directly fine-tuned for KD as they are not optimized to account for user's temporal typing information (e.g., hold time and flight time). To overcome this limitation, we propose TempCharBERT, an architecture that incorporates temporal-character information in the embedding layer of CharBERT. This allows modeling keystroke dynamics for the purpose of user identification and authentication. Our results show a significant improvement with this customization. We also showed the feasibility of training TempCharBERT on a federated learning settings in order to foster data privacy.
Pressure-sensitive smart textiles are widely applied in the fields of healthcare, sports monitoring, and intelligent homes. The integration of devices embedded with pressure sensing arrays is expected to enable comprehensive scene coverage and multi-device integration. However, the implementation of identity recognition, a fundamental function in this context, relies on extensive device-specific datasets due to variations in pressure distribution across different devices. To address this challenge, we propose a novel user identification method based on contrastive learning. We design two parallel branches to facilitate user identification on both new and existing devices respectively, employing supervised contrastive learning in the feature space to promote domain unification. When encountering new devices, extensive data collection efforts are not required; instead, user identification can be achieved using limited data consisting of only a few simple postures. Through experimentation with two 8-subject pressure datasets (BedPressure and ChrPressure), our proposed method demonstrates the capability to achieve user identification across 12 sitting scenarios using only a dataset containing 2 postures. Our average recognition accuracy reaches 79.05%, representing an improvement of 2.62% over the best baseline model.
User identification through smartphones and wearable sensors holds promise but faces challenges from variability in user activities and sampling windows. This paper presents a method that takes into account uncertainties to enhance the performance of user identification. The conventional sliding window technique is commonly employed for segmenting data, but using small windows can decrease classification performance by creating similar instances with different labels. Conversely, larger windows introduce concept drift resulting from mixed activity patterns. To tackle these challenges, the proposed method assesses the prediction uncertainty of a CNN classifier trained on small window sizes using the Monte Carlo Dropout technique and combines the predictions within a decision window. Uncertainty scores assist in discounting uncertain predictions during the final decision-making. Through experiments on five real-world datasets, the study demonstrates improved performance in identifying users across a range of activities compared to existing methods. It was also directly compared to state-of-the-art methods using two well-known datasets, improving accuracy by 1.29% in one case and 7.98% in the other. These findings validate the effectiveness of the new approach for continuous user identification, even when faced with unpredictable user behavior.
We present a new dataset of "free roaming" (FR) and "targeted roaming" (TR): a pool of 41 participants is asked to walk around a university campus (FR) or is asked to find a particular room within a library (TR). Eye movements are recorded using a commodity wearable eye tracker (Pupil Labs Neon at 200Hz). On this dataset we investigate the accuracy of user identification using a previously known machine learning pipeline where a Radial Basis Function Network (RBFN) is used as classifier. Our highest accuracies are 87.3% for FR and 89.4% for TR. This should be compared to 95.3% which is the (corresponding) highest accuracy we are aware of (achieved in a laboratory setting using the "RAN" stimulus of the BioEye 2015 competition dataset). To the best of our knowledge, our results are the first that study user identification in a non laboratory setting; such settings are often more feasible than laboratory settings and may include further advantages. The minimum duration of each recording is 263s for FR and 154s for TR. Our best accuracies are obtained when restricting to 120s and 140s for FR and TR respectively, always cut from the end of the trajectories (both for the training and testing sessions). If we cut the same length from the beginning, then accuracies are 12.2% lower for FR and around 6.4% lower for TR. On the full trajectories accuracies are lower by 5% and 52% for FR and TR. We also investigate the impact of including higher order velocity derivatives (such as acceleration, jerk, or jounce).
In recent years, numerous researchers have begun investigating how virtual reality (VR) tracking and interaction data can be used for a variety of machine learning purposes, including user identification, predicting cybersickness, and estimating learning gains. One constraint for this research area is the dearth of open datasets. In this paper, we present a new open dataset captured with our VR-based Full-scale Assembly Simulation Testbed (FAST). This dataset consists of data collected from 108 participants (50 females, 56 males, 2 non-binary) learning how to assemble two distinct full-scale structures in VR. In addition to explaining how the dataset was collected and describing the data included, we discuss how the dataset may be used by future researchers.
Radio frequency (RF) signals have facilitated the development of non-contact human monitoring tasks, such as vital signs measurement, activity recognition, and user identification. In some specific scenarios, an RF signal analysis framework may prioritize the performance of one task over that of others. In response to this requirement, we employ a multi-objective optimization approach inspired by biological principles to select discriminative features that enhance the accuracy of breathing patterns recognition while simultaneously impeding the identification of individual users. This approach is validated using a novel vital signs dataset consisting of 50 subjects engaged in four distinct breathing patterns. Our findings indicate a remarkable result: a substantial divergence in accuracy between breathing recognition and user identification. As a complementary viewpoint, we present a contrariwise result to maximize user identification accuracy and minimize the system's capacity for breathing activity recognition.
This work, in a pioneering approach, attempts to build a biometric system that works purely based on the fluid mechanics governing exhaled breath. We test the hypothesis that the structure of turbulence in exhaled human breath can be exploited to build biometric algorithms. This work relies on the idea that the extrathoracic airway is unique for every individual, making the exhaled breath a biomarker. Methods including classical multi-dimensional hypothesis testing approach and machine learning models are employed in building user authentication algorithms, namely user confirmation and user identification. A user confirmation algorithm tries to verify whether a user is the person they claim to be. A user identification algorithm tries to identify a user's identity with no prior information available. A dataset of exhaled breath time series samples from 94 human subjects was used to evaluate the performance of these algorithms. The user confirmation algorithms performed exceedingly well for the given dataset with over $97\%$ true confirmation rate. The machine learning based algorithm achieved a good true confirmation rate, reiterating our understanding of why machine learning based algorithms typically outperform classical hypothesis test based algorithms. The user identification algorithm performs reasonably well with the provided dataset with over $50\%$ of the users identified as being within two possible suspects. We show surprisingly unique turbulent signatures in the exhaled breath that have not been discovered before. In addition to discussions on a novel biometric system, we make arguments to utilise this idea as a tool to gain insights into the morphometric variation of extrathoracic airway across individuals. Such tools are expected to have future potential in the area of personalised medicines.
This paper studies the poisoning attack and defense interactions in a federated learning (FL) system, specifically in the context of wireless signal classification using deep learning for next-generation (NextG) communications. FL collectively trains a global model without the need for clients to exchange their data samples. By leveraging geographically dispersed clients, the trained global model can be used for incumbent user identification, facilitating spectrum sharing. However, in this distributed learning system, the presence of malicious clients introduces the risk of poisoning the training data to manipulate the global model through falsified local model exchanges. To address this challenge, a proactive defense mechanism is employed in this paper to make informed decisions regarding the admission or rejection of clients participating in FL systems. Consequently, the attack-defense interactions are modeled as a game, centered around the underlying admission and poisoning decisions. First, performance bounds are established, encompassing the best and worst strategies for attackers and defenders. Subsequently, the attack and defense utilities are characterized within the Nash equilibrium, where no player can unilaterally improve its performance given the fixed strategies of others. The results offer insights into novel operational modes that safeguard FL systems against poisoning attacks by quantifying the performance of both attacks and defenses in the context of NextG communications.
Biometrics is used to authenticate an individual based on physiological or behavioral traits. Mouse dynamics is an example of a behavioral biometric that can be used to perform continuous authentication as protection against security breaches. Recent research on mouse dynamics has shown promising results in identifying users; however, it has not yet reached an acceptable level of accuracy. In this paper, an empirical evaluation of different classification techniques is conducted on a mouse dynamics dataset, the Balabit Mouse Challenge dataset. User identification is carried out using three mouse actions: mouse move, point and click, and drag and drop. Verification and authentication methods are conducted using three machine-learning classifiers: the Decision Tree classifier, the K-Nearest Neighbors classifier, and the Random Forest classifier. The results show that the three classifiers can distinguish between a genuine user and an impostor with a relatively high degree of accuracy. In the verification mode, all the classifiers achieve a perfect accuracy of 100%. In authentication mode, all three classifiers achieved the highest accuracy (ACC) and Area Under Curve (AUC) from scenario B using the point and click action data: (Decision Tree ACC:87.6%, AUC:90.3%), (K-Nearest Neighbors ACC:99.3%, AUC:99.9%), and (Random Forest ACC:89.9%, AUC:92.5%).
Human activity recognition (HAR) is a key challenge in pervasive computing and its solutions have been presented based on various disciplines. Specifically, for HAR in a smart space without privacy and accessibility issues, data streams generated by deployed pervasive sensors are leveraged. In this paper, we focus on a group activity by which a group of users perform a collaborative task without user identification and propose an efficient group activity recognition scheme which extracts causality patterns from pervasive sensor event sequences generated by a group of users to support as good recognition accuracy as the state-of-the-art graphical model. To filter out irrelevant noise events from a given data stream, a set of rules is leveraged to highlight causally related events. Then, a pattern-tree algorithm extracts frequent causal patterns by means of a growing tree structure. Based on the extracted patterns, a weighted sum-based pattern matching algorithm computes the likelihoods of stored group activities to the given test event sequence by means of matched event pattern counts for group activity recognition. We evaluate the proposed scheme using the data collected from our testbed and CASAS datasets where users perform their tasks on a daily basis and validate its effectiveness in a real environment. Experiment results show that the proposed scheme performs higher recognition accuracy and with a small amount of runtime overhead than the existing schemes.
This paper provides a solution for the activity detection and channel estimation problem in grant-free access with correlated device activity patterns. In particular, we consider a machine-type communications (MTC) network operating in event-triggered traffic mode, where the devices are distributed over clusters with an activity behaviour that exhibits both intra-cluster and inner-cluster sparsity patterns. Furthermore, to model the network's intra-cluster and inner-cluster sparsity, we propose a structured sparsity-inducing spike-and-slab prior which provides a flexible approach to encode the prior information about the correlated sparse activity pattern. Furthermore, we drive a Bayesian inference scheme based on the expectation propagation (EP) framework to solve the JUICE problem. Numerical results highlight the significant gains obtained by the proposed structured sparsity-inducing spike-and-slab prior in terms of both user identification accuracy and channel estimation performance.
This paper addresses the joint user identification and channel estimation (JUICE) problem in machine-type communications under the practical spatially correlated channels model with unknown covariance matrices. Furthermore, we consider an MTC network with hierarchical user activity patterns following an event-triggered traffic mode. Therein the users are distributed over clusters with a structured sporadic activity behaviour that exhibits both cluster-level and intra-cluster sparsity patterns. To solve the JUICE problem, we first leverage the concept of strong priors and propose a hierarchical-sparsity-inducing spike-and-slab prior to model the structured sparse activity pattern. Subsequently, we derive a Bayesian inference scheme by coupling the expectation propagation (EP) algorithm with the expectation maximization (EM) framework. Second, we reformulate the JUICE as a maximum a posteriori (MAP) estimation problem and propose a computationally-efficient solution based on the alternating direction method of multipliers (ADMM). More precisely, we relax the strong spike-and-slab prior with a cluster-sparsity-promoting prior based on the long-sum penalty. We then derive an ADMM algorithm that solves the MAP problem through a sequence of closed-form updates. Numerical results highlight the significant performance significant gains obtained by the proposed algorithms, as well as their robustness against various assumptions on the users sparse activity behaviour.