The Internet of Things (IoT) is enabled by the latest developments in smart sensors, communication technologies, and Internet protocols with broad applications. Collecting data from IoT and generating information from these data become tedious tasks in real-life applications when missing data are encountered in datasets. It is of critical importance to deal with the missing data timely for intelligent decision-making. Hence, this survey attempts to provide a structured and comprehensive overview of the research on the imputation of incomplete data in IoT. The article starts by providing an overview of incomplete data based on the architecture of IoT. Then, it discusses the various strategies to handle the missing data, the assumptions used, the computing platform, and the issues related to them. The article also explores the application of imputation in the area of IoT. We encourage researchers and data analysts to use known imputation techniques and discuss various issues and challenges. Finally, potential future directions regarding the method are suggested. We believe this survey will provide a better understanding of the research of incomplete data and serve as a guide for future research.

Energy efficiency, reliability and real-time are three key requirements of mission-critical embedded systems. Existing approaches over emphasize the worst case design of real-time embedded systems, which will lead to serious waste of resources. In this paper, we aim at the energy-efficient design of soft real-time and reliable applications on uniprocessor embedded systems. We consider soft real-time tasks with stochastic execution durations regarding certain distributions. Thereby, we provide real-time guarantee with probability consideration. We utilize Dynamic Voltage and Frequency Scaling (DVFS) for saving energy, and also take into account the impact of DVFS on reliability. Our objective is to minimize the expected energy consumption of the system subject to statistical reliability and deadline constraints. The design optimization problem is a typical multidimensional multiple-choice knapsack problem, which is NP-hard. We first propose a dynamic programming based optimal algorithm to solve the problem. To reduce the time complexity, we then develop a (1+β)-approximation algorithm based on a binary search approach, where β is the approximating factor. The approximation algorithm can obtain the near-optimal solution with at most (1+β) times of optimal energy cost under given real-time and reliability constraints and has fully polynomial time complexity. Extensive experiments and a real-life synthetic application are conducted to evaluate the performance of the proposed techniques. Compared with existing approaches, the approximation approach can save much energy with low time overhead while guaranteeing the statistical deadline and reliability constraints.

In this article, we approach to construct reliable deep neural networks (DNNs) for safety-critical artificial intelligent applications. We propose to modify rectified linear unit (ReLU), a commonly used activation function in DNNs, to tolerate the faults incurred by bit-flip perturbation on weights. Through theoretic analysis of the fault propagation in the layers with ReLU activation, we observe that bounding the output of ReLU activation can help to tolerate the weight faults. Then, we propose a novel ReLU design called boundary-aware ReLU (BReLU) to improve the reliability of DNNs, in which an upper bound of ReLU is determined such that the deviation between the boundary and original outputs cannot affect the final result. We propose a gradient-ascent-based algorithm to find the boundaries for BReLU activations of all DNN layers. Without retraining the network, our approach is cost effective and practical when deployed in safety-critical artificial intelligent systems. Detailed experiments and real-life application benchmarking demonstrate that our approach can improve the accuracy of DNN VGG16 from 16.7% to 82.6% on average assuming the practical weight faults, with only 13% memory and 2.78% time overhead, respectively.

As an emerging threat to deep neural networks (DNNs), backdoor attacks have received increasing attentions due to the challenges posed by the lack of transparency inherent in DNNs. In this article, we develop an efficient algorithm from the interpretability of DNNs to defend against backdoor attacks to DNN models. To extract critical neurons, we deploy sets of control gates following neurons in layers, and the function of a DNN model can be interpreted as semantic sensitivities of neurons to input samples. A backdoor identification approach, derived from the activation frequency distribution on critical neurons, is proposed to reveal anomalies of particular neurons produced by backdoor attacks. Subsequently, a feasible and fine-grained pruning strategy is introduced to eliminate backdoors hidden in DNN models, without the need of retraining. Extensive experiments demonstrate that the proposed algorithm can identify and eliminate malicious backdoors efficiently in both single-target and multitarget scenarios with the performance of a DNN model retained to a large extent.

This paper approaches to design an attack-aware detection and defense framework to resist adversarial attacks on the security-critical artificial intelligent systems. We first make efforts to test the performances of adversarial attacks and present Classifying and Grading Rule (CGR) for the fine-grained grouping of adversarial example attacks. According to CGR, adversarial attacks can be divided into six groups. Then, we propose a feature squeezing and CGR-based detector to detect adversarial attacks, which can be aware of the detailed attack group and is evaluated to be effective by extensive experiments. We also test the defense performances of typical defense methods against these six groups of adversarial attacks, and finally give the defense recommendations for each type of adversarial attack.