arXiv subjects

J. Morris Chang

Publications and source records attributed to J. Morris Chang.

At least 19 recordsLinked to original sources

arXiv2026

Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.

cs.RO↗

arXiv2025

Advancing Practical Homomorphic Encryption for Federated Learning: Theoretical Guarantees and Efficiency Optimizations

Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping raw data locally stored on client devices, preventing access from other clients or the central server. However, recent studies reveal that sharing model gradients creates vulnerability to Model Inversion Attacks, particularly Deep Leakage from Gradients (DLG), which reconstructs private training data from shared gradients. While Homomorphic Encryption has been proposed as a promising defense mechanism to protect gradient privacy, fully encrypting all model gradients incurs high computational overhead. Selective encryption approaches aim to balance privacy protection with computational efficiency by encrypting only specific gradient components. However, the existing literature largely overlooks a theoretical exploration of the spectral behavior of encrypted versus unencrypted parameters, relying instead primarily on empirical evaluations. To address this gap, this paper presents a framework for theoretical analysis of the underlying principles of selective encryption as a defense against model inversion attacks. We then provide a comprehensive empirical study that identifies and quantifies the critical factors, such as model complexity, encryption ratios, and exposed gradients, that influence defense effectiveness. Our theoretical framework clarifies the relationship between gradient selection and privacy preservation, while our experimental evaluation demonstrates how these factors shape the robustness of defenses against model inversion attacks. Collectively, these contributions advance the understanding of selective encryption mechanisms and offer principled guidance for designing efficient, scalable, privacy-preserving federated learning systems.

cs.CR↗

arXiv2023

Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation

Neural Machine Translation (NMT) models have become successful, but their performance remains poor when translating on new domains with a limited number of data. In this paper, we present a novel approach Epi-Curriculum to address low-resource domain adaptation (DA), which contains a new episodic training framework along with denoised curriculum learning. Our episodic training framework enhances the model's robustness to domain shift by episodically exposing the encoder/decoder to an inexperienced decoder/encoder. The denoised curriculum learning filters the noised data and further improves the model's adaptability by gradually guiding the learning process from easy to more difficult tasks. Experiments on English-German and English-Romanian translation show that: (i) Epi-Curriculum improves both model's robustness and adaptability in seen and unseen domains; (ii) Our episodic training framework enhances the encoder and decoder's robustness to domain shift.

cs.LG↗

arXiv2023

Towards Implementing Energy-aware Data-driven Intelligence for Smart Health Applications on Mobile Platforms

Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have enabled high-performance deep learning on mobile platforms. These advancements have revolutionized the capabilities of today's mobile applications in different dimensions to perform data-driven intelligence locally, particularly for smart health applications. Unlike traditional machine learning (ML) architectures, modern on-device deep learning frameworks are proficient in utilizing computing resources in mobile platforms seamlessly, in terms of producing highly accurate results in less inference time. However, on the flip side, energy resources in a mobile device are typically limited. Hence, whenever a complex Deep Neural Network (DNN) architecture is fed into the on-device deep learning framework, while it achieves high prediction accuracy (and performance), it also urges huge energy demands during the runtime. Therefore, managing these resources efficiently within the spectrum of performance and energy efficiency is the newest challenge for any mobile application featuring data-driven intelligence beyond experimental evaluations. In this paper, first, we provide a timely review of recent advancements in on-device deep learning while empirically evaluating the performance metrics of current state-of-the-art ML architectures and conventional ML approaches with the emphasis given on energy characteristics by deploying them on a smart health application. With that, we are introducing a new framework through an energy-aware, adaptive model comprehension and realization (EAMCR) approach that can be utilized to make more robust and efficient inference decisions based on the available computing/energy resources in the mobile device during the runtime.

cs.LG↗

arXiv2022

MC-GEN:Multi-level Clustering for Private Synthetic Data Generation

With the development of machine learning and data science, data sharing is very common between companies and research institutes to avoid data scarcity. However, sharing original datasets that contain private information can cause privacy leakage. A reliable solution is to utilize private synthetic datasets which preserve statistical information from original datasets. In this paper, we propose MC-GEN, a privacy-preserving synthetic data generation method under differential privacy guarantee for machine learning classification tasks. MC-GEN applies multi-level clustering and differential private generative model to improve the utility of synthetic data. In the experimental evaluation, we evaluated the effects of parameters and the effectiveness of MC-GEN. The results showed that MC-GEN can achieve significant effectiveness under certain privacy guarantees on multiple classification tasks. Moreover, we compare MC-GEN with three existing methods. The results showed that MC-GEN outperforms other methods in terms of utility.

cs.LG↗

arXiv2022

IMUNet: Efficient Regression Architecture for IMU Navigation and Positioning

Data-driven based method for navigation and positioning has absorbed attention in recent years and it outperforms all its competitor methods in terms of accuracy and efficiency. This paper introduces a new architecture called IMUNet which is accurate and efficient for position estimation on edge device implementation receiving a sequence of raw IMU measurements. The architecture has been compared with one dimension version of the state-of-the-art CNN networks that have been introduced recently for edge device implementation in terms of accuracy and efficiency. Moreover, a new method for collecting a dataset using IMU sensors on cell phones and Google ARCore API has been proposed and a publicly available dataset has been recorded. A comprehensive evaluation using four different datasets as well as the proposed dataset and real device implementation has been done to prove the performance of the architecture. All the code in both Pytorch and Tensorflow framework as well as the Android application code have been shared to improve further research.

cs.RO↗

arXiv2022

Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation

The generalization capability of machine learning models, which refers to generalizing the knowledge for an "unseen" domain via learning from one or multiple seen domain(s), is of great importance to develop and deploy machine learning applications in the real-world conditions. Domain Generalization (DG) techniques aim to enhance such generalization capability of machine learning models, where the learnt feature representation and the classifier are two crucial factors to improve generalization and make decisions. In this paper, we propose Discriminative Adversarial Domain Generalization (DADG) with meta-learning-based cross-domain validation. Our proposed framework contains two main components that work synergistically to build a domain-generalized DNN model: (i) discriminative adversarial learning, which proactively learns a generalized feature representation on multiple "seen" domains, and (ii) meta-learning based cross-domain validation, which simulates train/test domain shift via applying meta-learning techniques in the training process. In the experimental evaluation, a comprehensive comparison has been made among our proposed approach and other existing approaches on three benchmark datasets. The results shown that DADG consistently outperforms a strong baseline DeepAll, and outperforms the other existing DG algorithms in most of the evaluation cases.

cs.LG↗

arXiv2022

SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification

Convolutional neural networks (CNNs) have achieved great success in skin lesion classification. A balanced dataset is required to train a good model. However, due to the appearance of different skin lesions in practice, severe or even deadliest skin lesion types (e.g., melanoma) naturally have quite small amount represented in a dataset. In that, classification performance degradation occurs widely, it is significantly important to have CNNs that work well on class imbalanced skin lesion image dataset. In this paper, we propose SuperCon, a two-stage training strategy to overcome the class imbalance problem on skin lesion classification. It contains two stages: (i) representation training that tries to learn a feature representation that closely aligned among intra-classes and distantly apart from inter-classes, and (ii) classifier fine-tuning that aims to learn a classifier that correctly predict the label based on the learnt representations. In the experimental evaluation, extensive comparisons have been made among our approach and other existing approaches on skin lesion benchmark datasets. The results show that our two-stage training strategy effectively addresses the class imbalance classification problem, and significantly improves existing works in terms of F1-score and AUC score, resulting in state-of-the-art performance.

cs.CV↗

arXiv2022

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation

Deep learning often requires a large amount of data. In real-world applications, e.g., healthcare applications, the data collected by a single organization (e.g., hospital) is often limited, and the majority of massive and diverse data is often segregated across multiple organizations. As such, it motivates the researchers to conduct distributed deep learning, where the data user would like to build DL models using the data segregated across multiple different data owners. However, this could lead to severe privacy concerns due to the sensitive nature of the data, thus the data owners would be hesitant and reluctant to participate. We propose LDP-DL, a privacy-preserving distributed deep learning framework via local differential privacy and knowledge distillation, where each data owner learns a teacher model using its own (local) private dataset, and the data user learns a student model to mimic the output of the ensemble of the teacher models. In the experimental evaluation, a comprehensive comparison has been made among our proposed approach (i.e., LDP-DL), DP-SGD, PATE and DP-FL, using three popular deep learning benchmark datasets (i.e., CIFAR10, MNIST and FashionMNIST). The experimental results show that LDP-DL consistently outperforms the other competitors in terms of privacy budget and model accuracy.

cs.LG↗

arXiv2021

Contrastive Self-supervised Neural Architecture Search

This paper proposes a novel cell-based neural architecture search algorithm (NAS), which completely alleviates the expensive costs of data labeling inherited from supervised learning. Our algorithm capitalizes on the effectiveness of self-supervised learning for image representations, which is an increasingly crucial topic of computer vision. First, using only a small amount of unlabeled train data under contrastive self-supervised learning allow us to search on a more extensive search space, discovering better neural architectures without surging the computational resources. Second, we entirely relieve the cost for labeled data (by contrastive loss) in the search stage without compromising architectures' final performance in the evaluation phase. Finally, we tackle the inherent discrete search space of the NAS problem by sequential model-based optimization via the tree-parzen estimator (SMBO-TPE), enabling us to reduce the computational expense response surface significantly. An extensive number of experiments empirically show that our search algorithm can achieve state-of-the-art results with better efficiency in data labeling cost, searching time, and accuracy in final validation.

cs.CV↗

arXiv2021

Generating Black-Box Adversarial Examples in Sparse Domain

Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although state-of-the-art CNNs provide high accuracy in many applications, recent investigations show that such networks are highly vulnerable to adversarial attacks. The black-box adversarial attack is one type of attack that the attacker does not have any knowledge about the model or the training dataset, but it has some input data set and their labels. In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed. Our investigation shows that large sparse (LaS) components play a critical role in the performance of image classifiers. Under this presumption, to generate adversarial example, we transfer an image into a sparse domain and put a threshold to choose only k LaS components. In contrast to the very recent works that randomly perturb k low frequency (LoF) components, we perturb k LaS components either randomly (query-based) or in the direction of the most correlated sparse signal from a different class. We show that LaS components contain some middle or higher frequency components information which leads fooling image classifiers with a fewer number of queries. We demonstrate the effectiveness of this approach by fooling six state-of-the-art image classifiers, the TensorFlow Lite (TFLite) model of Google Cloud Vision platform, and YOLOv5 model as an object detection algorithm. Mean squared error (MSE) and peak signal to noise ratio (PSNR) are used as quality metrics. We also present a theoretical proof to connect these metrics to the level of perturbation in the sparse domain.

cs.LG↗

arXiv2021

COVID-19 Pneumonia Severity Prediction using Hybrid Convolution-Attention Neural Architectures

This study proposed a novel framework for COVID-19 severity prediction, which is a combination of data-centric and model-centric approaches. First, we propose a data-centric pre-training for extremely scare data scenarios of the investigating dataset. Second, we propose two hybrid convolution-attention neural architectures that leverage the self-attention from the Transformer and the Dense Associative Memory (Modern Hopfield networks). Our proposed approach achieves significant improvement from the conventional baseline approach. The best model from our proposed approach achieves $R^2 = 0.85 \pm 0.05$ and Pearson correlation coefficient $ρ= 0.92 \pm 0.02$ in geographic extend and $R^2 = 0.72 \pm 0.09, ρ= 0.85\pm 0.06$ in opacity prediction.

eess.IV↗

arXiv2021

SEC-NoSQL: Towards Implementing High Performance Security-as-a-Service for NoSQL Databases

During the last few years, the explosion of Big Data has prompted cloud infrastructures to provide cloud-based database services as cost effective, efficient and scalable solutions to store and process large volume of data. Hence, NoSQL databases became more and more popular because of their inherent features of better performance and high scalability compared to other relational databases. However, with this deployment architecture where the information is stored in a public cloud, protection against the sensitive data is still being a major concern. Since the data owner does not have the full control over his sensitive data in a cloud-based database solution, many organizations are reluctant to move forward with Database-as-a-Service (DBaaS) solutions. Some of the recent work addressed this issue by introducing additional layers to provide encryption mechanisms to encrypt data, however, these approaches are more application specific and they need to be properly evaluated to ensure whether they can achieve high performance with the scalability when it comes to large volume of data in a cloud-based production environment. This paper proposes a practical system design and implementation to provide Security-as-a-Service for NoSQL databases (SEC-NoSQL) while supporting the execution of query over encrypted data with guaranteed level of system performance. Several different models of implementations are proposed, and their performance is evaluated using YCSB benchmark considering large number of clients processing simultaneously. Experimental results show that our design fits well on encrypted data while maintaining the high performance and scalability. Moreover, to deploy our solution as a cloud-based service, a practical guide establishing Service Level Agreement (SLA) is also included.

cs.DB↗

arXiv2021

ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the majority of devices are harnessing the cloud computing methodology in which outstanding deep learning models are responsible for analyzing the data on the server. This can bring the communication cost for the devices and make the whole system useless in those times where the communication is not available. In this paper, a new framework for deploying on IoT devices has been proposed which can take advantage of both the cloud and the on-device models by extracting the meta-information from each sample's classification result and evaluating the classification's performance for the necessity of sending the sample to the server. Experimental results show that only 40 percent of the test data should be sent to the server using this technique and the overall accuracy of the framework is 92 percent which improves the accuracy of both client and server models.

cs.DC↗

arXiv2021

A compressive multi-kernel method for privacy-preserving machine learning

As the analytic tools become more powerful, and more data are generated on a daily basis, the issue of data privacy arises. This leads to the study of the design of privacy-preserving machine learning algorithms. Given two objectives, namely, utility maximization and privacy-loss minimization, this work is based on two previously non-intersecting regimes -- Compressive Privacy and multi-kernel method. Compressive Privacy is a privacy framework that employs utility-preserving lossy-encoding scheme to protect the privacy of the data, while multi-kernel method is a kernel based machine learning regime that explores the idea of using multiple kernels for building better predictors. The compressive multi-kernel method proposed consists of two stages -- the compression stage and the multi-kernel stage. The compression stage follows the Compressive Privacy paradigm to provide the desired privacy protection. Each kernel matrix is compressed with a lossy projection matrix derived from the Discriminant Component Analysis (DCA). The multi-kernel stage uses the signal-to-noise ratio (SNR) score of each kernel to non-uniformly combine multiple compressive kernels. The proposed method is evaluated on two mobile-sensing datasets -- MHEALTH and HAR -- where activity recognition is defined as utility and person identification is defined as privacy. The results show that the compression regime is successful in privacy preservation as the privacy classification accuracies are almost at the random-guess level in all experiments. On the other hand, the novel SNR-based multi-kernel shows utility classification accuracy improvement upon the state-of-the-art in both datasets. These results indicate a promising direction for research in privacy-preserving machine learning.

cs.LG↗

arXiv2020

CS-AF: A Cost-sensitive Multi-classifier Active Fusion Framework for Skin Lesion Classification

Convolutional neural networks (CNNs) have achieved the state-of-the-art performance in skin lesion analysis. Compared with single CNN classifier, combining the results of multiple classifiers via fusion approaches shows to be more effective and robust. Since the skin lesion datasets are usually limited and statistically biased, while designing an effective fusion approach, it is important to consider not only the performance of each classifier on the training/validation dataset, but also the relative discriminative power (e.g., confidence) of each classifier regarding an individual sample in the testing phase, which calls for an active fusion approach. Furthermore, in skin lesion analysis, the data of certain classes (e.g., the benign lesions) is usually abundant making them an over-represented majority, while the data of some other classes (e.g., the cancerous lesions) is deficient, making them an underrepresented minority. It is more crucial to precisely identify the samples from an underrepresented (i.e., in terms of the amount of data) but more important minority class (e.g., certain cancerous lesion). In other words, misclassifying a more severe lesion to a benign or less severe lesion should have relative more cost (e.g., money, time and even lives). To address such challenges, we present CS-AF, a cost-sensitive multi-classifier active fusion framework for skin lesion classification. In the experimental evaluation, we prepared 96 base classifiers (of 12 CNN architectures) on the ISIC research datasets. Our experimental results show that our framework consistently outperforms the static fusion competitors.

cs.CV↗

arXiv2020

SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System

As the advancement of deep learning (DL), the Internet of Things and cloud computing techniques for biomedical and healthcare problems, mobile healthcare systems have received unprecedented attention. Since DL techniques usually require enormous amount of computation, most of them cannot be directly deployed on the resource-constrained mobile and IoT devices. Hence, most of the mobile healthcare systems leverage the cloud computing infrastructure, where the data collected by the mobile and IoT devices would be transmitted to the cloud computing platforms for analysis. However, in the contested environments, relying on the cloud might not be practical at all times. For instance, the satellite communication might be denied or disrupted. We propose SAIA, a Split Artificial Intelligence Architecture for mobile healthcare systems. Unlike traditional approaches for artificial intelligence (AI) which solely exploits the computational power of the cloud server, SAIA could not only relies on the cloud computing infrastructure while the wireless communication is available, but also utilizes the lightweight AI solutions that work locally on the client side, hence, it can work even when the communication is impeded. In SAIA, we propose a meta-information based decision unit, that could tune whether a sample captured by the client should be operated by the embedded AI (i.e., keeping on the client) or the networked AI (i.e., sending to the server), under different conditions. In our experimental evaluation, extensive experiments have been conducted on two popular healthcare datasets. Our results show that SAIA consistently outperforms its baselines in terms of both effectiveness and efficiency.

cs.AI↗

arXiv2020

Utility-aware Privacy-preserving Data Releasing

In the big data era, more and more cloud-based data-driven applications are developed that leverage individual data to provide certain valuable services (the utilities). On the other hand, since the same set of individual data could be utilized to infer the individual's certain sensitive information, it creates new channels to snoop the individual's privacy. Hence it is of great importance to develop techniques that enable the data owners to release privatized data, that can still be utilized for certain premised intended purpose. Existing data releasing approaches, however, are either privacy-emphasized (no consideration on utility) or utility-driven (no guarantees on privacy). In this work, we propose a two-step perturbation-based utility-aware privacy-preserving data releasing framework. First, certain predefined privacy and utility problems are learned from the public domain data (background knowledge). Later, our approach leverages the learned knowledge to precisely perturb the data owners' data into privatized data that can be successfully utilized for certain intended purpose (learning to succeed), without jeopardizing certain predefined privacy (training to fail). Extensive experiments have been conducted on Human Activity Recognition, Census Income and Bank Marketing datasets to demonstrate the effectiveness and practicality of our framework.

cs.CR↗