Huanle Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Huanle Zhang has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Prasant Mohapatra
Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA
8 shared publications - Xiuzhen Cheng
Shandong University
8 shared publications - Pengfei Hu
Shandong University
7 shared publications - Xin Liu
Department of Computer Science, University of California, Davis, CA 95616, USA
6 shared publications Lei Fu
4 shared publications- Xianglong Zhang
School of Computer Science and Technology, Shandong University, Jinan, China
4 shared publications
Latest Publications
- Open Access
- 10 April 2027
- Published by Association for Computing Machinery (ACM)
- p. 501-519
Hardware Support for Deterministic User-Level Interrupts in Real-Time Embedded Systems
Modern real-time embedded systems demand strong component isolation for safety and security. Normally, interrupts are handled in kernel mode before they are passed on to the application, which induces high latency if isolated components need to react to external events. Thus, hardware-assisted, low-latency user-level interrupts are highly desirable. Nevertheless, existing hardware mechanisms only optimize average-case performance while neglecting worst-case latency for sensitive applications including autonomous vehicles and robots. To overcome this limitation, we propose a novel open-source hardware extension that integrates spatial isolation setup, execution budget management, cross-domain nesting, and accelerated context switching for user-level interrupts with tight latency. It enables direct, deterministic delivery upon user-level interrupt arrival-without kernel intervention-even when the target process is dormant. Across the entire design space, the best-performing design reduces worst-case latency by over 50×, while the lowest-overhead design incurs only a 23% increase in core area (2% of total die area) and a 3% increase in dynamic power. To the best of our knowledge, this is the first integrated mechanism to guarantee multi-tenant user-level interrupt delivery with a nanosecond-scale yet bounded worst-case latency. It provides a holistic solution for developing secure, dependable, and low-latency cyber-physical systems in real-time consolidation scenarios.
- 10 April 2027
- Published by Association for Computing Machinery (ACM)
- p. 501-519
Open AccessHardware Support for Deterministic User-Level Interrupts in Real-Time Embedded Systems
Modern real-time embedded systems demand strong component isolation for safety and security. Normally, interrupts are handled in kernel mode before they are passed on to the application, which induces high latency if isolated components need to react to external events. Thus, hardware-assisted, low-latency user-level interrupts are highly desirable. Nevertheless, existing hardware mechanisms only optimize average-case performance while neglecting worst-case latency for sensitive applications including autonomous vehicles and robots. To overcome this limitation, we propose a novel open-source hardware extension that integrates spatial isolation setup, execution budget management, cross-domain nesting, and accelerated context switching for user-level interrupts with tight latency. It enables direct, deterministic delivery upon user-level interrupt arrival-without kernel intervention-even when the target process is dormant. Across the entire design space, the best-performing design reduces worst-case latency by over 50×, while the lowest-overhead design incurs only a 23% increase in core area (2% of total die area) and a 3% increase in dynamic power. To the best of our knowledge, this is the first integrated mechanism to guarantee multi-tenant user-level interrupt delivery with a nanosecond-scale yet bounded worst-case latency. It provides a holistic solution for developing secure, dependable, and low-latency cyber-physical systems in real-time consolidation scenarios.
- Open Access
- 26 May 2026
- Published by Elsevier in High-Confidence Computing
- Vol. 6 (3)
A survey on large-scale unobtrusive BMI estimation for public health
- 26 May 2026
- Published by Elsevier in High-Confidence Computing
- Vol. 6 (3)
Open AccessA survey on large-scale unobtrusive BMI estimation for public health
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (7) , 2389-2401
FVM: Practical Feather-Weight Virtualization on Commodity Microcontrollers
Recently, there has been an increasing drive to consolidate multiple microcontrollers into one physical entity, due to advantages in reducing overall costs, enhancing reliability, and simplifying hardware interconnections. To reduce consolidation engineering costs, minimizing system latency and memory footprint is important as well as maintaining compatibility with legacy software. In this paper, we propose a virtualization-based solution called Feather-weight Virtual Machine (FVM) that focuses on these goals. FVM enables low latency by specializing the virtualization model to Real-Time Operating Systems (RTOSes), achieves small footprint by adapting management policies to microcontroller memories, attains high compatibility by aligning with microcontroller ecosystem idiosyncrasies, finally allowing practical consolidation across a wide range of commodity microcontrollers. We implement and evaluate FVM on ARMv6-M, ARMv7-M, and RISC-V architectures with two toolchains and two RTOSes, and it can fit into 20 KiB of RAM with less than 5% latency bloat.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (7) , 2389-2401
FVM: Practical Feather-Weight Virtualization on Commodity Microcontrollers
Recently, there has been an increasing drive to consolidate multiple microcontrollers into one physical entity, due to advantages in reducing overall costs, enhancing reliability, and simplifying hardware interconnections. To reduce consolidation engineering costs, minimizing system latency and memory footprint is important as well as maintaining compatibility with legacy software. In this paper, we propose a virtualization-based solution called Feather-weight Virtual Machine (FVM) that focuses on these goals. FVM enables low latency by specializing the virtualization model to Real-Time Operating Systems (RTOSes), achieves small footprint by adapting management policies to microcontroller memories, attains high compatibility by aligning with microcontroller ecosystem idiosyncrasies, finally allowing practical consolidation across a wide range of commodity microcontrollers. We implement and evaluate FVM on ARMv6-M, ARMv7-M, and RISC-V architectures with two toolchains and two RTOSes, and it can fit into 20 KiB of RAM with less than 5% latency bloat.
- 20 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (5) , 4006-4021
Membership Inference Attacks Against Incremental Learning in IoT Devices
Internet of Things (IoT) devices are frequently deployed in highly dynamic environments and need to continuously learn new classes from data streams. Incremental Learning (IL) has gained popularity in IoT as it enables devices to learn new classes efficiently without retraining model entirely. IL involves fine-tuning the model using two sources of data: a small amount of representative samples from the original training dataset and samples from the new classes. However, both data sources are vulnerable to Membership Inference Attack (MIA). Fortunately, the existing MIAs result in poor performance against IL, because they ignore features such as the similarity between old and new models at the old classification layer. This paper presents the first MIA against IL, capable of determining not only whether a sample was used for training/fine-tuning but also distinguishing whether it belongs to the representative dataset or the new classes (unique in IL). Extensive experiments validate the effectiveness of our attack across four real-world datasets. Our attack achieves an average attack success rate of 74.03% in the white-box setting (model structure and parameters are known) and 70.08% in the black-box setting. Importantly, our attack is not sensitive to the IL hyper-parameters (e.g., distillation temperature), confirming its accurate, robust, and practical.
- 20 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (5) , 4006-4021
Membership Inference Attacks Against Incremental Learning in IoT Devices
Internet of Things (IoT) devices are frequently deployed in highly dynamic environments and need to continuously learn new classes from data streams. Incremental Learning (IL) has gained popularity in IoT as it enables devices to learn new classes efficiently without retraining model entirely. IL involves fine-tuning the model using two sources of data: a small amount of representative samples from the original training dataset and samples from the new classes. However, both data sources are vulnerable to Membership Inference Attack (MIA). Fortunately, the existing MIAs result in poor performance against IL, because they ignore features such as the similarity between old and new models at the old classification layer. This paper presents the first MIA against IL, capable of determining not only whether a sample was used for training/fine-tuning but also distinguishing whether it belongs to the representative dataset or the new classes (unique in IL). Extensive experiments validate the effectiveness of our attack across four real-world datasets. Our attack achieves an average attack success rate of 74.03% in the white-box setting (model structure and parameters are known) and 70.08% in the black-box setting. Importantly, our attack is not sensitive to the IL hyper-parameters (e.g., distillation temperature), confirming its accurate, robust, and practical.
- 22 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (2) , 1579-1589
IoT-Enabled Supply Chain Management From a Customer Perspective: Challenges and Opportunities
Supply chain management (SCM), a critical factor in enhancing companies’ efficiency and competitiveness, has received significant attention from both industry and academia. Beyond the flow of products from supplier to customer, SCM also involves the flow of information necessary to monitor, track, and optimize the entire product lifecycle. Consequently, integrating the information flow in SCM with the Internet of Things (IoT) is imperative, as IoT provides the ability to onboard, interconnect, interact with, and sense products. However, IoT-enabled SCM also presents unique challenges, such as managing large volumes of data, ensuring credible and traceable data sources, and achieving low-cost, seamless connectivity. In this article, we systematically present recent advances in leveraging IoT to build robust and effective SCM systems. Unlike existing surveys and overviews, this article focuses on the customer side as customers are the destination of the information flow and tightly coupled with IoT networks. We offer deep insights into the principles, challenges, and research opportunities in IoT-enabled SCM, aiming to assist IoT practitioners in understanding and designing IoT solutions for SCM.
- 22 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (2) , 1579-1589
IoT-Enabled Supply Chain Management From a Customer Perspective: Challenges and Opportunities
Supply chain management (SCM), a critical factor in enhancing companies’ efficiency and competitiveness, has received significant attention from both industry and academia. Beyond the flow of products from supplier to customer, SCM also involves the flow of information necessary to monitor, track, and optimize the entire product lifecycle. Consequently, integrating the information flow in SCM with the Internet of Things (IoT) is imperative, as IoT provides the ability to onboard, interconnect, interact with, and sense products. However, IoT-enabled SCM also presents unique challenges, such as managing large volumes of data, ensuring credible and traceable data sources, and achieving low-cost, seamless connectivity. In this article, we systematically present recent advances in leveraging IoT to build robust and effective SCM systems. Unlike existing surveys and overviews, this article focuses on the customer side as customers are the destination of the information flow and tightly coupled with IoT networks. We offer deep insights into the principles, challenges, and research opportunities in IoT-enabled SCM, aiming to assist IoT practitioners in understanding and designing IoT solutions for SCM.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (3) , 1715-1730
Model Poisoning Attack Against Neural Network Interpreters in IoT Devices
Neural network models have become integral to Internet of Things (IoT) systems, with applications spanning from industrial automation to critical infrastructure management. Despite their prevalence, the deployment of these models within IoT systems introduces distinctive security vulnerabilities. In particular, adversaries may execute model poisoning attacks, which aim to alter the decision-making processes of embedded models, leading to erroneous outcomes. Existing model poisoning attacks necessitate access to extensive auxiliary datasets, such as the training dataset itself or one with same distribution. These requirements often render such attacks impractical in IoT contexts, given the constrained storage and computational resources of IoT devices. This paper proposes the first model poisoning attack against interpreters without auxiliary datasets to manipulate the model's behavior. We evaluate the attack on three real-world datasets, and results indicate that this attack can successfully coerce the targeted interpreters to produce outcomes aligned with an adversary's intentions, while maintaining nearly indistinguishable performance from the original model, thereby ensuring its stealthiness. Furthermore, beyond directly affected interpreters, our experiments reveal that four additional interpreters coupled to the poisoned model are indirectly influenced, underscoring the attack's transferability.
- 24 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (3) , 1715-1730
Model Poisoning Attack Against Neural Network Interpreters in IoT Devices
Neural network models have become integral to Internet of Things (IoT) systems, with applications spanning from industrial automation to critical infrastructure management. Despite their prevalence, the deployment of these models within IoT systems introduces distinctive security vulnerabilities. In particular, adversaries may execute model poisoning attacks, which aim to alter the decision-making processes of embedded models, leading to erroneous outcomes. Existing model poisoning attacks necessitate access to extensive auxiliary datasets, such as the training dataset itself or one with same distribution. These requirements often render such attacks impractical in IoT contexts, given the constrained storage and computational resources of IoT devices. This paper proposes the first model poisoning attack against interpreters without auxiliary datasets to manipulate the model's behavior. We evaluate the attack on three real-world datasets, and results indicate that this attack can successfully coerce the targeted interpreters to produce outcomes aligned with an adversary's intentions, while maintaining nearly indistinguishable performance from the original model, thereby ensuring its stealthiness. Furthermore, beyond directly affected interpreters, our experiments reveal that four additional interpreters coupled to the poisoned model are indirectly influenced, underscoring the attack's transferability.
- Open Access
Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches
Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantifications of those differences outside of the gait laboratory have been elusive. In this work, we measured vertical, mediolateral, and anteroposterior acceleration using a waist-worn iPhone accelerometer during ambulation across a typical range of velocities. Fifteen TD and fifteen DMD children from 3 to 16 years of age underwent eight walking/running activities, including five 25 m walk/run speed-calibration tests at a slow walk to running speeds (SC-L1 to SC-L5), a 6-min walk test (6MWT), a 100 m fast walk/jog/run (100MRW), and a free walk (FW). For clinical anchoring purposes, participants completed a Northstar Ambulatory Assessment (NSAA). We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data. Extracted temporospatial gait CFs showed reduced step length and a greater mediolateral component of total power (TP) consistent with shorter strides and Trendelenberg-like gait commonly observed in DMD. ML approaches using temporospatial gait CFs and raw data varied in effectiveness at differentiating between DMD and TD controls at different speeds, with an accuracy of up to 100%. We demonstrate that by using ML with accelerometer data from a consumer-grade smartphone, we can capture DMD-associated gait characteristics in toddlers to teens.
Open AccessGait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches
Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantifications of those differences outside of the gait laboratory have been elusive. In this work, we measured vertical, mediolateral, and anteroposterior acceleration using a waist-worn iPhone accelerometer during ambulation across a typical range of velocities. Fifteen TD and fifteen DMD children from 3 to 16 years of age underwent eight walking/running activities, including five 25 m walk/run speed-calibration tests at a slow walk to running speeds (SC-L1 to SC-L5), a 6-min walk test (6MWT), a 100 m fast walk/jog/run (100MRW), and a free walk (FW). For clinical anchoring purposes, participants completed a Northstar Ambulatory Assessment (NSAA). We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data. Extracted temporospatial gait CFs showed reduced step length and a greater mediolateral component of total power (TP) consistent with shorter strides and Trendelenberg-like gait commonly observed in DMD. ML approaches using temporospatial gait CFs and raw data varied in effectiveness at differentiating between DMD and TD controls at different speeds, with an accuracy of up to 100%. We demonstrate that by using ML with accelerometer data from a consumer-grade smartphone, we can capture DMD-associated gait characteristics in toddlers to teens.
- Top Cited Papers
- 28 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (24) , 21811-21819
Client Selection in Federated Learning: Principles, Challenges, and Opportunities
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. Thus, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement. In this paper, we systematically present recent advances in the emerging field of FL client selection and its challenges and research opportunities. We hope to facilitate practitioners in choosing the most suitable client selection mechanisms for their applications, as well as inspire researchers and newcomers to better understand this exciting research topic.
- 28 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (24) , 21811-21819
Top Cited PapersClient Selection in Federated Learning: Principles, Challenges, and Opportunities
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. Thus, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement. In this paper, we systematically present recent advances in the emerging field of FL client selection and its challenges and research opportunities. We hope to facilitate practitioners in choosing the most suitable client selection mechanisms for their applications, as well as inspire researchers and newcomers to better understand this exciting research topic.
- 25 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 72 (10) , 2978-2989
Model Poisoning Attack on Neural Network Without Reference Data
Due to the substantial computational cost of neural network training, adopting third-party models has become increasingly popular. However, recent works demonstrate that third-party models can be poisoned. Nonetheless, most model poisoning attacks require reference data, e.g., training dataset or data belonging to the target label, making them difficult to launch in practice. In this paper, we propose a reference data independent model poisoning attack that can (1) directly search for sensitive features with respect to the target label, (2) quantify the positive and negative effects of the model parameters on sensitive features, and (3) accomplish the training of poisoned model by our parameter selective update strategy. The extensive evaluation on datasets with a few classes and numerous classes show that the attack is (I) effective: the trigger input can be labeled as a deliberate class by the poisoned model with high probability; (II) covert: the performance of the poisoned model is almost indistinguishable from the intact model on non-trigger inputs; and (III) straightforward: an adversary only needs a little background knowledge to launch the attack. Overall, the evaluation results show that our attack achieves $95\%$ , $100\%$ , $81\%$ , $96\%$ , and $96\%$ success rates on Cifar10, Cifar100, ISIC2018, FaceScrub, and ImageNet datasets, respectively.
- 25 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 72 (10) , 2978-2989
Model Poisoning Attack on Neural Network Without Reference Data
Due to the substantial computational cost of neural network training, adopting third-party models has become increasingly popular. However, recent works demonstrate that third-party models can be poisoned. Nonetheless, most model poisoning attacks require reference data, e.g., training dataset or data belonging to the target label, making them difficult to launch in practice. In this paper, we propose a reference data independent model poisoning attack that can (1) directly search for sensitive features with respect to the target label, (2) quantify the positive and negative effects of the model parameters on sensitive features, and (3) accomplish the training of poisoned model by our parameter selective update strategy. The extensive evaluation on datasets with a few classes and numerous classes show that the attack is (I) effective: the trigger input can be labeled as a deliberate class by the poisoned model with high probability; (II) covert: the performance of the poisoned model is almost indistinguishable from the intact model on non-trigger inputs; and (III) straightforward: an adversary only needs a little background knowledge to launch the attack. Overall, the evaluation results show that our attack achieves $95\%$ , $100\%$ , $81\%$ , $96\%$ , and $96\%$ success rates on Cifar10, Cifar100, ISIC2018, FaceScrub, and ImageNet datasets, respectively.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 2122-2131
Ginver: Generative Model Inversion Attacks Against Collaborative Inference
Deep Learning (DL) has been widely adopted in almost all domains, from threat recognition to medical diagnosis. Albeit its supreme model accuracy, DL imposes a heavy burden on devices as it incurs overwhelming system overhead to execute DL models, especially on Internet-of-Things (IoT) and edge devices. Collaborative inference is a promising approach to supporting DL models, by which the data owner (the victim) runs the first layers of the model on her local device and then a cloud provider (the adversary) runs the remaining layers of the model. Compared to offloading the entire model to the cloud, the collaborative inference approach is more data privacy-preserving as the owner’s model input is not exposed to outsiders. However, we show in this paper that the adversary can restore the victim’s model input by exploiting the output of the victim’s local model. Our attack is dubbed Ginver 1: Generative model inversion attacks against collaborative inference. Once trained, Ginver can infer the victim’s unseen model inputs without remaking the inversion attack model and thus has the generative capability. We extensively evaluate Ginver under different settings (e.g., white-box and black-box of the victim’s local model) and applications (e.g., CIFAR10 and FaceScrub datasets). The experimental results show that Ginver recovers high-quality images from the victims.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 2122-2131
Open AccessGinver: Generative Model Inversion Attacks Against Collaborative Inference
Deep Learning (DL) has been widely adopted in almost all domains, from threat recognition to medical diagnosis. Albeit its supreme model accuracy, DL imposes a heavy burden on devices as it incurs overwhelming system overhead to execute DL models, especially on Internet-of-Things (IoT) and edge devices. Collaborative inference is a promising approach to supporting DL models, by which the data owner (the victim) runs the first layers of the model on her local device and then a cloud provider (the adversary) runs the remaining layers of the model. Compared to offloading the entire model to the cloud, the collaborative inference approach is more data privacy-preserving as the owner’s model input is not exposed to outsiders. However, we show in this paper that the adversary can restore the victim’s model input by exploiting the output of the victim’s local model. Our attack is dubbed Ginver 1: Generative model inversion attacks against collaborative inference. Once trained, Ginver can infer the victim’s unseen model inputs without remaking the inversion attack model and thus has the generative capability. We extensively evaluate Ginver under different settings (e.g., white-box and black-box of the victim’s local model) and applications (e.g., CIFAR10 and FaceScrub datasets). The experimental results show that Ginver recovers high-quality images from the victims.