Search for: All records

AI's widespread integration has led to neural networks (NN) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained platforms demand compact networks. This study introduces VeriCompress, a tool that automates the search and training of compressed models with robustness guarantees. These models are well-suited for safety-critical applications and adhere to predefined architecture and size limitations, making them deployable on resource-restricted platforms. The method trains models 2-3 times faster than the state-of-the-art approaches, surpassing them by average accuracy and robustness gains of 15.1 and 9.8 percentage points, respectively. When deployed on a resource-restricted generic platform, these models require 5-8 times less memory and 2-4 times less inference time than models used in verified robustness literature. Our comprehensive evaluation across various model architectures and datasets, including MNIST, CIFAR, SVHN, and a relevant pedestrian detection dataset, showcases VeriCompress's capacity to identify compressed verified robust models with reduced computation overhead compared to current standards. This underscores its potential as a valuable tool for end users, such as developers of safety-critical applications on edge or Internet of Things platforms, empowering them to create suitable models for safety-critical, resource-constrained platforms in their respective domains. 

Stress impacts our physical and mental health as well as our social life. A passive and contactless indoor stress monitoring system can unlock numerous important applications such as workplace productivity assessment, smart homes, and personalized mental health monitoring. While the thermal signatures from a user's body captured by a thermal camera can provide important information about the ``fight-flight'' response of the sympathetic and parasympathetic nervous system, relying solely on thermal imaging for training a stress prediction model often lead to overfitting and consequently a suboptimal performance. This paper addresses this challenge by introducing ThermaStrain, a novel co-teaching framework that achieves high-stress prediction performance by transferring knowledge from the wearable modality to the contactless thermal modality. During training, ThermaStrain incorporates a wearable electrodermal activity (EDA) sensor to generate stress-indicative representations from thermal videos, emulating stress-indicative representations from a wearable EDA sensor. During testing, only thermal sensing is used, and stress-indicative patterns from thermal data and emulated EDA representations are extracted to improve stress assessment. The study collected a comprehensive dataset with thermal video and EDA data under various stress conditions and distances. ThermaStrain achieves an F1 score of $0.8293$ in binary stress classification, outperforming the thermal-only baseline approach by over 9\%. Extensive evaluations highlight ThermaStrain's effectiveness in recognizing stress-indicative attributes, its adaptability across distances and stress scenarios, real-time executability on edge platforms, its applicability to multi-individual sensing, ability to function on limited visibility and unfamiliar conditions, and the advantages of its co-teaching approach. These evaluations validate ThermaStrain's fidelity and its potential for enhancing stress assessment. 

Stress impacts our physical and mental health as well as our social life. A passive and contactless indoor stress monitoring system can unlock numerous important applications such as workplace productivity assessment, smart homes, and personalized mental health monitoring. While the thermal signatures from a user's body captured by a thermal camera can provide important information about the fight-flight response of the sympathetic and parasympathetic nervous system, relying solely on thermal imaging for training a stress prediction model often lead to overfitting and consequently a suboptimal performance. This paper addresses this challenge by introducing ThermaStrain, a novel co-teaching framework that achieves high-stress prediction performance by transferring knowledge from the wearable modality to the contactless thermal modality. During training, ThermaStrain incorporates a wearable electrodermal activity (EDA) sensor to generate stress-indicative representations from thermal videos, emulating stress-indicative representations from a wearable EDA sensor. During testing, only thermal sensing is used, and stress-indicative patterns from thermal data and emulated EDA representations are extracted to improve stress assessment. The study collected a comprehensive dataset with thermal video and EDA data under various stress conditions and distances. ThermaStrain achieves an F1 score of 0.8293 in binary stress classification, outperforming the thermal-only baseline approach by over 9%. Extensive evaluations highlight ThermaStrain's effectiveness in recognizing stress-indicative attributes, its adaptability across distances and stress scenarios, real-time executability on edge platforms, its applicability to multi-individual sensing, ability to function on limited visibility and unfamiliar conditions, and the advantages of its co-teaching approach. These evaluations validate ThermaStrain's fidelity and its potential for enhancing stress assessment. 

Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies. These VA services raise privacy concerns, especially due to their access to our speech. This work considers one such use case: the unaccountable and unauthorized surveillance of a user's emotion via speech emotion recognition (SER). This paper presents DARE-GP, a solution that creates additive noise to mask users' emotional information while preserving the transcription-relevant portions of their speech. DARE-GP does this by using a constrained genetic programming approach to learn the spectral frequency traits that depict target users' emotional content, and then generating a universal adversarial audio perturbation that provides this privacy protection. Unlike existing works, DARE-GP provides: a) real-time protection of previously unheard utterances, b) against previously unseen black-box SER classifiers, c) while protecting speech transcription, and d) does so in a realistic, acoustic environment. Further, this evasion is robust against defenses employed by a knowledgeable adversary. The evaluations in this work culminate with acoustic evaluations against two off-the-shelf commercial smart speakers using a small-form-factor (raspberry pi) integrated with a wake-word system to evaluate the efficacy of its real-world, real-time deployment. 

The presented first-of-its-kind study effectively identifies and visualizes the second-by-second pattern differences in the physiological arousal of preschool-age children who do stutter (CWS) and who do not stutter (CWNS) while speaking perceptually fluently in two challenging conditions: speaking in stressful situations and narration. The first condition may affect children's speech due to high arousal; the latter introduces linguistic, cognitive, and communicative demands on speakers. We collected physiological parameters data from 70 children in the two target conditions. First, we adopt a novel modality-wise multiple-instance-learning (MI-MIL) approach to classify CWS vs. CWNS in different conditions effectively. The evaluation of this classifier addresses four critical research questions that align with state-of-the-art speech science studies' interests. Later, we leverage SHAP classifier interpretations to visualize the salient, fine-grain, and temporal physiological parameters unique to CWS at the population/group-level and personalized-level. While group-level identification of distinct patterns would enhance our understanding of stuttering etiology and development, the personalized-level identification would enable remote, continuous, and real-time assessment of stuttering children's physiological arousal, which may lead to personalized, just-in-time interventions, resulting in an improvement in speech fluency. The presented MI-MIL approach is novel, generalizable to different domains, and real-time executable. Finally, comprehensive evaluations are done on multiple datasets, presented framework, and several baselines that identified notable insights on CWSs' physiological arousal during speech production. 

The recent prevalence of machine learning-based techniques and smart device embedded sensors has enabled widespread human-centric sensing applications. However, these applications are vulnerable to false data injection attacks (FDIA) that alter a portion of the victim's sensory signal with forged data comprising a targeted trait. Such a mixture of forged and valid signals successfully deceives the continuous authentication system (CAS) to accept it as an authentic signal. Simultaneously, introducing a targeted trait in the signal misleads human-centric applications to generate specific targeted inference; that may cause adverse outcomes. This paper evaluates the FDIA's deception efficacy on sensor-based authentication and human-centric sensing applications simultaneously using two modalities - accelerometer, blood volume pulse signals. We identify variations of the FDIA such as different forged signal ratios, smoothed and non-smoothed attack samples. Notably, we present a novel attack detection framework named Siamese-MIL that leverages the Siamese neural networks' generalizable discriminative capability and multiple instance learning paradigms through a unique sensor data representation. Our exhaustive evaluation demonstrates Siamese-MIL's real-time execution capability and high efficacy in different attack variations, sensors, and applications.