Novel Adaptive DNN Partitioning Method Based on Image-Stream Pipeline Inference between the Edge and Cloud

The prevalent usage and unparalleled recent success of Deep Neural Network (DNN) applications have raised the concern of protecting their Intellectual Property (IP) rights in different business models to prevent the theft of trade secrets. In this article, we propose a lightweight, generic, key-based DNN IP protection methodology, NN-Lock , to defend against unauthorized usage of stolen DNN models. NN-Lock utilizes SBox, a cryptographic primitive, with good security properties to encrypt each parameter of a trained DNN model with the secret keys derived from a master key through a key-scheduling algorithm. The method ensures that only an authorized user with a correct master key can accurately use the locked DNN model. Evaluation results of NN-Lock on a Google Coral edge device for various DNN architectures on several datasets show that for an incorrect master key, the accuracy of a locked model is that of a random classifier. The dense network of encrypted parameters makes the method robust against the model fine-tuning attack and a novel approximation attack using the Genetic Algorithm, which achieves reasonable success against another recent IP protection scheme called HPNN Chakraborty et al. 2020 . The security evaluation of NN-Lock against other families of attacks demonstrates its soundness in practical scenarios. NN-Lock does not modify any internal structure of a DNN model, making it scalable for all of the existing DNN implementations without adversely affecting their performance.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

With the rapid development of the Internet of Things (IoT) and communication technology, deep neural network (DNN) applications, such as medical imaging, speech transcription, handwritten text recognition, have been widely used in IoT devices. However, due to resource constraints on these devices, e.g., limited memory capacity, weak computing capacity, and low battery capacity, IoT devices cannot support complicated DNN operation effectively and, thus, fail to fulfill the requirements of Quality of Service of mobile users. One promising approach is to migrate the DNN model to a remote cloud server to reduce the computing burden on IoT devices. Unfortunately, it still suffers from high delay and low bandwidth when communicating with cloud servers. Although the transmission delay of the edge server is low, its computing capacity lacks scalability and elasticity.To make matters worse, in the real world, the wireless connection between IoT devices and the cloud is intermittent, which can cause offloading failures during large-scale DNN data transmission. In this article, we describe a DNN model migration framework to overcome the abovementioned challenges, which consists of three parts: DNN model preprocessing, partition-offloading plan, and partition-uploading plan. Accordingly, we introduce the operation of the DNN migration and the available methods for each part. In addition, we improve the DNN partition-uploading plan in a multiuser edge-cloud collaborative computing environment. Finally, we highlight the important challenges of achieving more efficient DNN migration and point out the unresolved issues of DNN migration, which may shed light on future research directions.

Online dynamic stability analysis plays a key role in modern power systems and is becoming even more vital with the penetration of Distributed Energy Resources (DERs). Identification of an accurate lower-order model for the ‘external system” makes it possible to carry out the stability analysis of a study system faster than the analysis for the original detailed system. However, the identified lower-order model becomes invalid when the operating state changes in the power system. ‘Black box’ representation of the ‘external system’ with the application of Deep Neural Networks (DNN) is widely discussed in the literature. In such equivalent models, the DNN response changes based on two aspects i.e. the operating point of the power system and the location/type of the fault. In this paper, a clustering algorithm is proposed to identify the clusters of the ‘external system’ models for different states of the power system, and a DNN is trained for each cluster. The clustering algorithm is based on the pre-fault steady-state power flow from the ‘external system’ to the ‘study system’, which is a reflection of changes in the system state. Mean Absolute Error (MAE) between responses of the actual fault and the predicted fault is used to evaluate the accuracy of the identified system. The proposed technique is easy to implement and requires a lesser number of DNN models compared to identifying an individual DNN model for each operating point to represent the ‘external system’.

Architecture reverse engineering has become an emerging attack against deep neural network (DNN) implementations. Several prior works have utilized side-channel leakage to recover the model architecture while the an DNN is executing on a hardware acceleration platform. In this work, we target an open-source deep-learning accelerator, Versatile Tensor Accelerator (VTA), and utilize electromagnetic (EM) side-channel leakage to comprehensively learn the association between DNN architecture configurations and EM emanations. We also consider the holistic system–including the low-level tensor program code of the VTA accelerator on a Xilinx FPGA, and explore the effect of such low-level configurations on the EM leakage. Our study demonstrates that both the optimization and configuration of tensor programs will affect the EM side-channel leakage.Gaining knowledge of the association between low-level tensor program and the EM emanations, we propose NNReArch, a lightweight tensor program scheduling framework against side-channel-based DNN model architecture reverse engineering. Specifically, NNReArch targets reshaping the EM traces of different DNN operators, through scheduling the tensor program execution of the DNN model so as to confuse the adversary. NNReArch is a comprehensive protection framework supporting two modes, a balanced mode that strikes a balance between the DNN model confidentiality and execution performance, and a secure mode where the most secure setting is chosen. We implement and evaluate the proposed framework on the open-source VTA with state-of-the-art DNN architectures. The experimental results demonstrate that NNReArch can efficiently enhance the model architecture security with a small performance overhead. In addition, the proposed obfuscation technique makes reverse engineering of the DNN architecture significantly harder.

Survey on Deep Neural Networks in Speech and Vision Systems

Deep Neural Network (DNN) models have achieved excellent performance in many inference tasks and have been widely used in many intelligent applications. However, DNN models often require a lot of computational resources to complete the inference tasks, which hinders the deployment of such models to resource‐constrained edge devices. In order to extend the application scenarios of DNN models, the edge‐cloud collaborative inference methods, represented by model partition, have attracted much research attention in recent years. In scenarios that have multiple edge devices deployed, the edge‐cloud collaborative inference method requires partial migration of tasks, but traditional scheduling methods only migrate tasks at the task level. In this paper, we propose two task scheduling methods, which can solve the problem of partial migration of tasks in multiedge scenarios. The first scheduling method is based on the optimal cutting of a single DNN. The cutting positions of all the models are the same, regardless of the influence of external factors. This method is suitable for chain and directed acyclic graph‐ (DAG‐) type DNNs. The second scheduling method takes external factors such as congestion and queuing delay at the cloud side into consideration, which dynamically selects the cutting position of each DNN to optimize the overall delay and thus is applicable to chain DNN models. The experimental results show that, compared with the baseline method, our proposed scheduling method can reduce the delay by up to 6.48x.

Batteries are the most expensive component of battery electric vehicles (BEVs), but they degrade over time and battery operation. State of health (SOH) forecasting models learn how battery operation over long-time periods of weeks or months influences battery aging. Currently, existing methods for SOH forecasting of lithium-ion batteries based on deep neural network (DNN) models lack explainability of their forecasts due to their inherent black box character. However, the explainability of forecasts is essential to build user trust into the forecasting models. In this work, we address this problem from two perspectives: First, we compared four machine learning (ML) models like decision tree and random forest, which are inherently transparent, to two new DNN architectures with a more inherent black box character. Second, we proposed a new method using Gaussian-filtered saliency maps to visualize battery operational states that are relevant to DNN models. This method is applied to the best DNN models previously trained. We used an extensive data corpus consisting of five public data sets with different operational conditions, battery types, and aging trajectories. Furthermore, we show that the Gaussian-filtered saliency maps meaningfully visualize battery operational states that are consistent with findings from controlled laboratory aging experiments. Thus, this work was able to add transparency and interpretability to the SOH forecasting results of two state-of-the-art DNNs, while maintaining their superior performance compared to transparent ML models, while mitigating their inherent black box character.

Traditionally Deep Neural Networks (DNNs) services are deployed in the cloud, due to the computation-intensive DNN models. In recent years, as emerging edge computing provides new possibilities for DNN applications, we have opportunities to process DNN models in the cloud and on the device collaboratively, i.e., edge-cloud computing. Since cloud and edge devices demonstrate significant diversity on inference latency, network transmission overhead, memory capacity and power consumption, it is a big challenge to determine the DNN model deployment in the cloud and on edge devices. In this paper, we characterize the behaviours of three types of DNN models, i.e., CNN, LSTM and MLP, on four types of platforms, i.e., server-class CPU, server-class GPU, embedded device with GPU, and smart-phones. Our experimental results demonstrate that we can carefully tune a deployment strategy for DNN models in the cloud, and on big and (or) little cores of the edge device, to balance performance and power consumption.

Deep learning is being incorporated in many modern software systems. Deep learning approaches train a deep neural network (DNN) model using training examples, and then use the DNN model for prediction. While the structure of a DNN model as layers is observable, the model is treated in its entirety as a monolithic component. To change the logic implemented by the model, e.g. to add/remove logic that recognizes inputs belonging to a certain class, or to replace the logic with an alternative, the training examples need to be changed and the DNN needs to be retrained using the new set of examples. We argue that decomposing a DNN into DNN modules— akin to decomposing a monolithic software code into modules—can bring the benefits of modularity to deep learning. In this work, we develop a methodology for decomposing DNNs for multi-class problems into DNN modules. For four canonical problems, namely MNIST, EMNIST, FMNIST, and KMNIST, we demonstrate that such decomposition enables reuse of DNN modules to create different DNNs, enables replacement of one DNN module in a DNN with another without needing to retrain. The DNN models formed by composing DNN modules are at least as good as traditional monolithic DNNs in terms of test accuracy for our problems.

PurposeSleep apnea (SA) is highly prevalent, but under diagnosed due to inaccessibility of sleep testing. To address this issue, portable devices for home sleep testing have been developed to provide convenience with reasonable accuracy in diagnosing SA. The objective of this study was to test the validity a novel portable sleep apnea testing device, BresoDX1, in SA diagnosis, via recording of trachea-sternal motion, tracheal sound and oximetry.Patients and MethodsAdults with a suspected sleep disorder were recruited to undergo in-laboratory polysomnography (PSG) and a simultaneous BresoDX1 recording. Data from BresoDX1 were collected and features related to breathing sounds, body motions and oximetry were extracted. A deep neural network (DNN) model was trained with 61-second epochs of the extracted features to detect apneas and hypopneas from which an apnea-hypopnea index (AHI) was calculated. The AHI estimated by BresoDX1 (AHIbreso) was compared to the AHI determined from PSG (AHIPSG) and the sensitivity and specificity of SA diagnosis were assessed at an AHIPSG ≥ 15.ResultsTwo-hundred thirty-three participants (mean ± SD) 50 ± 16 years of age, with BMI of 29.8 ± 6.6 and AHI of 19.5 ± 22.7, were included. There was a strong relationship between AHIbreso and AHIPSG (r = 0.91, p < 0.001). SA detection for an AHIPSG ≥ 15 was highly sensitive (90.0%) and specific (85.9%).ConclusionWe conclude that the DNN model we developed via recording and analyses of trachea-sternal motion and sound along with oximetry provides an accurate estimate of the AHIPSG with high sensitivity and specificity. Therefore, BresoDX1 is a simple, convenient and accurate portable SA monitoring device that could be employed for home SA testing in the future.

Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings

Small data sets make developing calibration models using deep neural networks difficult because it is easy to overfit the system. We developed two deep neural network architectures by revising two existing network architectures: the U-Net and the attention mechanism. The major changes were to use 1D convolutional layers to replace the fully connected layers. We also designed and combined average pooling and maximum pooling in our revised networks, respectively. We applied these revised network architectures to three publicly available data sets and the resulting calibration models can generate acceptable results for general quantitative analysis. It also generated rather good results for data sets that concern calibration transfer. It demonstrates that constructing network architectures by properly revising existing successful network architectures may provide additional choices in the exploration of the application of deep neural network in analytical chemistry.

Deep Neural Networks (DNNs) have been successfully applied to various real-world machine learning applications. However, performing large DNN inference tasks in real-time remains a challenge due to its substantial computational costs. Recently, Spiking Neural Networks (SNNs) have emerged as an alternative way of processing DNN'fs task. Due to its eventbased, data-driven computation, SNN reduces both inference latency and complexity. With efficient conversion methods from traditional DNN, SNN exhibits similar accuracy, while leveraging many state-of-the-art network models and training methods. In this work, an efficient neuromorphic hardware architecture for image recognition task is presented. To preserve accuracy, the analog-to-spiking conversion algorithm is adopted. The system aims to minimize hardware area cost and power consumption, enabling neuromorphic hardware processing in edge devices. Simulation results have shown that, with the MNIST digit recognition task, the system has achieved $\times 20$ reduction in terms of core area cost compared to the state-of-the-art works, with an accuracy of 94.4%, core area of 15 $\mu m^{2}$ at a maximum frequency of 250 MHz.

Deep neural network (DNN) models typically have many hyperparameters that can be configured to achieve optimal performance on a particular dataset. Practitioners usually tune the hyperparameters of their DNN models by training a number of trial models with different configurations of the hyperparameters, to find the optimal hyperparameter configuration that maximizes the training accuracy or minimizes the training loss. As such hyperparameter tuning usually focuses on the model accuracy or the loss function, it is not clear and remains under-explored how the process impacts other performance properties of DNN models, such as inference latency and model size. On the other hand, standard DNN models are often large in size and computing-intensive, prohibiting them from being directly deployed in resource-bounded environments such as mobile devices and Internet of Things (IoT) devices. To tackle this problem, various model optimization techniques (e.g., pruning or quantization) are proposed to make DNN models smaller and less computing-intensive so that they are better suited for resource-bounded environments. However, it is neither clear how the model optimization techniques impact other performance properties of DNN models such as inference latency and battery consumption, nor how the model optimization techniques impact the effect of hyperparameter tuning (i.e., the compounding effect). Therefore, in this paper, we perform a comprehensive study on four representative and widely-adopted DNN models, i.e., CNN image classification , Resnet-50 , CNN text classification , and LSTM sentiment classification , to investigate how different DNN model hyperparameters affect the standard DNN models, as well as how the hyperparameter tuning combined with model optimization affect the optimized DNN models, in terms of various performance properties (e.g., inference latency or battery consumption). Our empirical results indicate that tuning specific hyperparameters has heterogeneous impact on the performance of DNN models across different models and different performance properties. In particular, although the top tuned DNN models usually have very similar accuracy, they may have significantly different performance in terms of other aspects (e.g., inference latency). We also observe that model optimization has a confounding effect on the impact of hyperparameters on DNN model performance. For example, two sets of hyperparameters may result in standard models with similar performance but their performance may become significantly different after they are optimized and deployed on the mobile device. Our findings highlight that practitioners can benefit from paying attention to a variety of performance properties and the confounding effect of model optimization when tuning and optimizing their DNN models.