Robust DNN-based Decoder Model with an Embedded State-Space Model Layer.

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

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.

Heartbeat classification is a crucial step for arrhythmia diagnosis during electrocardiographic (ECG) analysis. The new scenario of wireless body sensor network- (WBSN-) enabled ECG monitoring puts forward a higher-level demand for this traditional ECG analysis task. Previously reported methods mainly addressed this requirement with the applications of a shallow structured classifier and expert-designed features. In this study, modified frequency slice wavelet transform (MFSWT) was firstly employed to produce the time-frequency image for heartbeat signal. Then the deep learning (DL) method was performed for the heartbeat classification. Here, we proposed a novel model incorporating automatic feature abstraction and a deep neural network (DNN) classifier. Features were automatically abstracted by the stacked denoising auto-encoder (SDA) from the transferred time-frequency image. DNN classifier was constructed by an encoder layer of SDA and a softmax layer. In addition, a deterministic patient-specific heartbeat classifier was achieved by fine-tuning on heartbeat samples, which included a small subset of individual samples. The performance of the proposed model was evaluated on the MIT-BIH arrhythmia database. Results showed that an overall accuracy of 97.5% was achieved using the proposed model, confirming that the proposed DNN model is a powerful tool for heartbeat pattern recognition.

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.

As a fundamental task in modern data mining, time series classification is powering mission-critical tasks including stock price prediction and network traffic analysis. Due to the non-linear structure of deep neural networks (DNN), deep learning has established as a promising solution to time series classification. However, the excessive learning capacity of DNNs may make them prone to threats of backdoor attacks, where an attacker embeds hidden functionalities (i.e., backdoor) to DNNs and activates the backdoor by specially-designed inputs (i.e., triggers). Despite extensive studies concerning backdoor attacks on image and text domains, there is little known about the vulnerability of DNN based time series classifiers against backdoor attacks. Due to the unique characteristics of time series data, most existing backdoor attack techniques fail to threaten time series classifiers. In this paper, through analyzing the key factors which influence the effectiveness of a backdoor, we systematize a list of practical principles for designing triggers on time series data. In this light, we propose a novel framework called TimeTrojan, which aims to learn to form the trigger pattern through a constrained multi-objective optimization. To solve the hereafter challenging optimization issue, we further design an iterative learning algorithm. Remarkably, the proposed framework is agnostic to a wide range of DNN classifiers. Extensive empirical results on 6 representative DNN classifiers and 6 real-world datasets validate the effectiveness of the proposed attack framework. In most cases, TimeTrojan successfully injects backdoors with 100% attack success rate without affecting the model accuracy on clean samples, which implies the complete control of the behavior of the DNN classifiers by the adversary.

Recent advances in programmed death-1 (PD-1) and programmed death-ligand 1 (PD-L1) immune checkpoint inhibitor (ICI) revolutionized the clinical practice in lung cancer treatment. The PD-L1 immunohistochemistry (IHC) test is a widely used biomarker for ICI responder in lung cancer. However, the accuracy of PD-L1 IHC test for selecting ICI responder is unsatisfactory, especially due to its low specificity. Therefore, methods which could effectively predict the efficacy of ICI are crucial for patient selection. In this article, we apply a deep neural network (DNN) to predict responders for anti-PD1 blockade on the basis of histopathological images of hematoxylin and eosin (H&E) stained tissue. The main difficulty to train DNN for responder prediction is the inability to accurately label at the image patch level. We employed a semi-supervised multi-instance learning (MIL) framework with adaptive positive patch selection in each region-of-interest (ROI). Using a dataset of 250 whole slide images (WSIs) of non-small cell lung cancer (111 responders and 139 nonresponders), we train a DNN-based MIL classifier on a case-level partition of the dataset (150 WSIs) and obtain an area under curve (AUC) of 0.773 for the test dataset (50 WSIs), which outperforms the PD-L1 IHC test (AUC=0.636). These results suggest that a DNN model can be used for assisting clinicians to make decision for treatment plan. We also confirm that the locations of adaptively selected positive patches can give valuable insights into the histological features associated with drug response.

In this work, a training method was proposed for Deep Neural Networks (DNNs) based on a two-stage structure. Local DNN models are trained in all local machines and uploaded to the center with partial training data. These local models are integrated as a new DNN model (combination DNN). With another DNN model (optimization DNN) connected, the combination DNN forms a global DNN model in the center. This results in greater accuracy than local DNN models with smaller amounts of data uploaded. In this case, the bandwidth of the uploaded data is saved, and the accuracy is maintained as well. Experiments are conducted on MNIST dataset, CIFAR-10 dataset and LFW dataset. The results show that with less training data uploaded, the global model produces greater accuracy than local models. Specifically, this method focuses on condition of big data.

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.

As training a high-performance deep neural network (DNN) model requires a large amount of data, powerful computing resources and expert knowledge, protecting well-trained DNN models from intellectual property (IP) infringement has raised serious concerns in recent years. Most existing methods using DNN watermarks to verify the ownership of the models after IP infringement occurs, which is reactive in the sense that they cannot prevent unauthorized users from using the model in the first place. Different from these methods, in this article, we propose an active authorization control and user’s fingerprint tracking method for the IP protection of DNN models by utilizing sample-specific backdoor attack. The proposed method inversely and multiplely exploits sample-specific trigger as the key to implement authorization control for DNN model, in which the generated triggers are imperceptible and sample-specific for clean images. Specifically, a U-Net model is used to generate backdoor instances. Then, the target model is trained on the clean images and backdoor instances, which are inversely labeled as wrong classes and correct classes, respectively. Only authorized users can use the target model normally by pre-processing the clean images through the U-Net model. Moreover, the images processed by the U-Net model will contain unique fingerprint that can be extracted to verify and track the corresponding user’s identity. This article is the first work that utilizes the sample-specific backdoor attack to implement active authorization control and user’s fingerprint management for DNN model under black-box scenarios. Extensive experimental results on ImageNet dataset and YouTube Aligned Face dataset demonstrate that the proposed method is effective in protecting the DNN model from unauthorized usage. Specifically, the protected model has a low inference accuracy (1.00%) for unauthorized users, while maintaining a normal inference accuracy (97.67%) for authorized users. Besides, the proposed method can achieve 100% fingerprint tracking success rates on both the ImageNet and YouTube Aligned Face datasets. Moreover, it is demonstrated that the proposed method is robust against fine-tuning attack, pruning attack, pruning attack with retraining, reverse-engineering attack, adaptive attack, and JPEG compression attack. The code is available at https://github.com/nuaaaisec/SSAT .

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.

Dynamic properties, such as shear modulus and damping ratio, are critical for civil engineering applications and essential for accurate dynamic response analysis. This study introduces a novel Deep Neural Network (DNN) approach to predict the normalized shear modulus (G/Gmax ) and damping ratio (D) of granular soils over a wide strain range. Utilising a comprehensive dataset from cyclic triaxial (CT) and resonant column (RC) tests, we developed a Deep Feed-Forward Neural Network (DFFNN) model. The model incorporates grading characteristics, shear strain, void ratio, mean effective confining pressure, consolidation stress ratio, and specimen preparation method as inputs. The DFFNN demonstrated high accuracy with testing results of 0.9830 for G/Gmax and 0.9396 for D, outperforming traditional empirical models and other intelligent techniques such as Shallow Neural Network (SNN), Support Vector Regression (SVR), and Gradient Boosting Regression (GBR). This data-driven approach offers a robust and adaptable method for predicting the dynamic properties of granular soils across diverse conditions.

Automatic recognition of surface defects for hot-rolled steel strip based on deep attention residual convolutional neural network

Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and confidentiality of user data within the general public when their data is processed and stored in an external server which has further fueled the need for developing such efficient neural networks for real-time inference on local embedded systems. The scope of our work presented in this paper is limited to image classification using a convolutional neural network. A Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN) widely used in the analysis of visual images captured by an image sensor, designed to extract information and convert it into meaningful representations for real-time inference of the input data. In this paper, we propose a neoteric variant of deep convolutional neural network architecture to ameliorate the performance of existing CNN architectures for real-time inference on embedded systems. We show that this architecture, dubbed CondenseNeXt, is remarkably efficient in comparison to the baseline neural network architecture, CondenseNet, by reducing trainable parameters and FLOPs required to train the network whilst maintaining a balance between the trained model size of less than 3.0 MB and accuracy trade-off resulting in an unprecedented computational efficiency.

Distant speech recognition (DSR) remains to be an open challenge, even for the state-of-the-art deep neural network (DNN) models. Previous work has attempted to improve DNNs under constantly distant speech. However, in real applications, the speaker-microphone distance (SMD) can be quite dynamic, varying even within a single utterance. This paper investigates how to alleviate the impact of dynamic SMD on DNN models. Our solution is to incorporate the frame-level SMD information into DNN training. Generation of the SMD information relies on a universal extractor that is learned on a meeting corpus. We study the utility of different architectures in instantiating the SMD extractor. On our target acoustic modeling task, two approaches are proposed to build distance-aware DNN models using the SMD information: simple concatenation and distance adaptive training (DAT). Our experiments show that in the simplest case, incorporating the SMD descriptors improves word error rates of DNNs by 5.6% relative. Further optimizing SMD extraction and integration results in more gains.

Deep neural networks (DNNs) are increasingly deployed in various fields. Despite their spectacular advances, DNNs are known to suffer from adversarial vulnerabilities. The robustness of DNNs is then threatened by leading them to misclassifications with unexpected inputs (adversarial examples). The fuzzing technique frequently used for testing traditional software has recently been adopted to evaluate the robustness of DNNs. Current DNN fuzzing techniques focus on image classification DNNs and generate test cases by mutations, e.g., image transformations and adversarial perturbations. However, mutation-based test cases usually lack diversity and have distribution deflection from the original DNN input space, which impacts the evaluation of DNNs. In this paper, we propose a generation-based fuzzing frame-work FuzzGAN to detect adversarial flaws existing in DNNs. We integrate the testing purpose and the guidance of the neuron coverage into the original objectives of auxiliary classifier generative adversarial networks. Hence, FuzzGAN learns the representation of a DNN's input space and generates test cases without the limitation of any concrete seed input. We evaluate the performance of FuzzGAN on two DNN models that have classical network structures and are trained on public datasets. The experiment results demonstrate that FuzzGAN can generate realistic, diverse and valid test cases and achieve high neuron coverage. Moreover, these test cases can be used to improve the performance of the target DNN through adversarial retraining.