A survey on privacy inference attacks and defenses in cloud-based Deep Neural Network

Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and analyzing massive data to boost advanced scientific development. It is not a surprise that cloud computing providers offer the cloud-based DNN as an out-of-the-box service. Though there are some benefits from the cloud-based DNN, the interaction mechanism among two or multiple entities in the cloud inevitably induces new privacy risks. This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services. We systematically and thoroughly review privacy attacks and defenses in the pipeline of cloud-based DNN service, i.e., data manipulation, training, and prediction. In particular, a new theory, called cloud-based ML privacy game, is extracted from the recently published literature to provide a deep understanding of state-of-the-art research. Finally, the challenges and future work are presented to help researchers to continue to push forward the competitions between privacy attackers and defenders.     

Origin of Hole-Trapping States in Solution-Processed Copper(I) Thiocyanate and Defect-Healing by I2 Doping

Solution-processed copper(I) thiocyanate (CuSCN) typically exhibits low crystallinity with short-range order; the defects result in a high density of trap states that limit the device's performance. Despite the extensive electronic applications of CuSCN, its defect properties are not understood in detail. Through X-ray absorption spectroscopy, pristine CuSCN prepared from the standard diethyl sulfide-based recipe is found to contain under-coordinated Cu atoms, pointing to the presence of SCN⁻ vacancies. A defect passivation strategy is introduced by adding solid I₂ to the processing solution. At small concentrations, the iodine is found to exist as I⁻ which can substitute for the missing SCN⁻ ligand, effectively healing the defective sites and restoring the coordination around Cu. Computational study results also verify this point. Applying I₂-doped CuSCN as a p-channel in thin-film transistors shows that the hole mobility increases by more than five times at the optimal doping concentration of 0.5 mol.%. Importantly, the on/off current ratio and the subthreshold characteristics also improve as the I₂ doping method leads to the defect-healing effect while avoiding the creation of detrimental impurity states. An analysis of the capacitance-voltage characteristics corroborates that the trap state density is reduced upon I₂ addition.     

Mitigating Detrimental Effect of Self-Doping Near the Anode in Highly Efficient Organic Solar Cells

Poly(3,4-ethylenedioxythiophene):polystyrene sulfonate (PEDOT:PSS) has been one of the most established hole transport layers (HTL) in organic solar cells (OSCs) for several decades. However, the presence of PSS⁻ ions is known to deteriorate device performance via a number of mechanisms including diffusion to the HTL-active layer interface and unwanted local chemical reactions. In this study, it is shown that PSS⁻ ions can also result in local p-doping in the high efficiency donor:non-fullerene acceptor blends – resulting in photocurrent loss. To address these issues, a facile and effective approach is reported to improve the OSC performance through a two-component hole transport layer (HTL) consisting of a self-assembled monolayer of 2PACz ([2-(9H-Carbazol-9-yl)ethyl]phosphonic acid) and PEDOT:PSS. The power conversion efficiency (PCE) of 17.1% using devices with PEDOT:PSS HTL improved to 17.7% when the PEDOT:PSS/2PACz two-component HTL is used. The improved performance is attributed to the overlaid 2PACz layer preventing the formation of an intermixed p-doped PSS⁻ ion rich region (≈5–10 nm) at the bulk heterojunction-HTL contact interface, resulting in decreased recombination losses and improved stability. Moreover, the 2PACz monolayer is also found to reduce electrical shunts that ultimately yield improved performance in large area devices with PCE enhanced from 12.3% to 13.3% in 1 cm² cells.     

An Optimized Deep-Learning-Based Low Power Approximate Multiplier Design

Approximate computing is a popular field for low power consumption that is used in several applications like image processing, video processing, multimedia and data mining. This Approximate computing is majorly performed with an arithmetic circuit particular with a multiplier. The multiplier is the most essential element used for approximate computing where the power consumption is majorly based on its performance. There are several researchers are worked on the approximate multiplier for power reduction for a few decades, but the design of low power approximate multiplier is not so easy. This seems a bigger challenge for digital industries to design an approximate multiplier with low power and minimum error rate with higher accuracy. To overcome these issues, the digital circuits are applied to the Deep Learning (DL) approaches for higher accuracy. In recent times, DL is the method that is used for higher learning and prediction accuracy in several fields. Therefore, the Long Short-Term Memory (LSTM) is a popular time series DL method is used in this work for approximate computing. To provide an optimal solution, the LSTM is combined with a meta-heuristics Jellyfish search optimisation technique to design an input aware deep learning-based approximate multiplier (DLAM). In this work, the jelly optimised LSTM model is used to enhance the error metrics performance of the Approximate multiplier. The optimal hyperparameters of the LSTM model are identified by jelly search optimisation. This fine-tuning is used to obtain an optimal solution to perform an LSTM with higher accuracy. The proposed pre-trained LSTM model is used to generate approximate design libraries for the different truncation levels as a function of area, delay, power and error metrics. The experimental results on an 8-bit multiplier with an image processing application shows that the proposed approximate computing multiplier achieved a superior area and power reduction with very good results on error rates.     

Optimal Artificial Intelligence Based Automated Skin Lesion Detection and Classification Model

Skin lesions have become a critical illness worldwide, and the earlier identification of skin lesions using dermoscopic images can raise the survival rate. Classification of the skin lesion from those dermoscopic images will be a tedious task. The accuracy of the classification of skin lesions is improved by the use of deep learning models. Recently, convolutional neural networks (CNN) have been established in this domain, and their techniques are extremely established for feature extraction, leading to enhanced classification. With this motivation, this study focuses on the design of artificial intelligence (AI) based solutions, particularly deep learning (DL) algorithms, to distinguish malignant skin lesions from benign lesions in dermoscopic images. This study presents an automated skin lesion detection and classification technique utilizing optimized stacked sparse autoencoder (OSSAE) based feature extractor with backpropagation neural network (BPNN), named the OSSAE-BPNN technique. The proposed technique contains a multi-level thresholding based segmentation technique for detecting the affected lesion region. In addition, the OSSAE based feature extractor and BPNN based classifier are employed for skin lesion diagnosis. Moreover, the parameter tuning of the SSAE model is carried out by the use of sea gull optimization (SGO) algorithm. To showcase the enhanced outcomes of the OSSAE-BPNN model, a comprehensive experimental analysis is performed on the benchmark dataset. The experimental findings demonstrated that the OSSAE-BPNN approach outperformed other current strategies in terms of several assessment metrics.     

基于深度卷积生成对抗网络的半生成式视频隐写方案

生成式隐写通过生成足够自然或真实的含密样本来隐藏秘密消息,是信息隐藏方向的研究热点,但目前在视频隐写领域的研究还比较少。结合数字化卡登格的思想,提出一种基于深度卷积生成对抗网络（DCGAN）的半生成式视频隐写方案。该方案中,设计了基于DCGAN的双流视频生成网络,用来生成视频的动态前景、静态后景与时空掩模三个部分,并以随机噪声驱动生成不同的视频。方案中的发送方可设定隐写阈值,在掩模中自适应地生成数字化卡登格,并将其作为隐写与提取的密钥;同时以前景作为载体,实现信息的最优嵌入。实验结果表明,该方案生成的含密视频具有良好的视觉质量,Frechet Inception距离（FID）值为90,且嵌入容量优于现有的生成式隐写方案,最高可达0.11 bpp,能够更高效地传输秘密消息。     

Excavator 3D pose estimation using deep learning and hybrid datasets

Earthwork operations are crucial parts of most construction projects. Heavy construction equipment and workers are often required to work in limited workspaces simultaneously. Struck-by accidents resulting from poor worker and equipment interactions account for a large proportion of accidents and fatalities on construction sites. The emerging technologies based on computer vision and artificial intelligence offer an opportunity to enhance construction safety through advanced monitoring utilizing site cameras. A crucial pre-requisite to the development of safety monitoring applications is the ability to identify accurately and localize the position of the equipment and its critical components in 3D space. This study proposes a workflow for excavator 3D pose estimation based on deep learning using RGB images. In the proposed workflow, an articulated 3D digital twin of an excavator is used to generate the necessary data for training a 3D pose estimation model. In addition, a method for generating hybrid datasets (simulation and laboratory) for adapting the 3D pose estimation model for various scenarios with different camera parameters is proposed. Evaluations prove the capability of the workflow in estimating the 3D pose of excavators. The study concludes by discussing the limitations and future research opportunities.     

F-BIDS: Federated-Blending based Intrusion Detection System

The rapid development of network communication along with the drastic increase in the number of smart devices has triggered a surge in network traffic, which can contain private data and in turn affect user privacy. Recently, Federated Learning (FL) has been proposed in Intrusion Detection Systems (IDS) to ensure attack detection, privacy preservation, and cost reduction, which are crucial issues in traditional centralized machine-learning-based IDS. However, FL-based approaches still exhibit vulnerabilities that can be exploited by adversaries to compromise user data. At the same time, meta-models (including the blending models) have been recognized as one of the solutions to improve generalization for attack detection and classification since they enhance generalization and predictive performances by combining multiple base models. Therefore, in this paper, we propose a Federated Blending model-driven IDS framework for the Internet of Things (IoT) and Industrial IoT (IIoT), called F-BIDS, in order to further protect the privacy of existing ML-based IDS. The proposition consists of a Decision Tree (DT) and Random Forest (RF) as base classifiers to first produce the meta-data. Then, the meta-classifier, which is a Neural Networks (NN) model, uses the meta-data during the federated training step, and finally, it makes the final classification on the test set. Specifically, in contrast to the classical FL approaches, the federated meta-classifier is trained on the meta-data (composite data) instead of user-sensitive data to further enhance privacy. To evaluate the performance of F-BIDS, we used the most recent and open cyber-security datasets, called Edge-IIoTset (published in 2022) and InSDN (in 2020). We chose these datasets because they are recent datasets and contain a large amount of network traffic including both malicious and benign traffic.     

Volt-VAR control for distribution networks with high penetration of DGs: An overview

Continuously improving the ability to accept distributed renewable energies is the trend of future grid development, and a large number of papers have been published in recent years to study the problem of Volt-VAR control (VVC) for distribution networks with high penetration of distributed generations. This paper summarizes the relevant modeling and solution methods for VVC problems, mainly including VVC based on multiple time scales, hierarchical partitioning, multi-stage and network reconstruction, in conjunction with the operational characteristics of distribution networks containing distributed renewable energies; meanwhile, it analyzes the advantages and disadvantages of traditional optimization methods, heuristic intelligent algorithms and random variable processing methods used to solve VVC problems, and then introduces the application of model-free deep reinforcement learning as a latest decision method in VVC of distribution networks. Most of the models and methods compiled in this article are from the research results of the last three years and have some reference value.     

雷达辐射源信号分选研究进展

雷达辐射源信号分选是雷达信号侦察的关键技术之一,同时也是战场态势感知的重要环节。该文系统梳理了雷达辐射源信号分选的主流技术,从基于脉间调制特征、基于脉内调制特征、基于机器学习的雷达辐射源信号分选3个角度阐述了目前雷达辐射源信号分选工作的主要研究方向及进展,并重点阐释了基于深度神经网络、数据流聚类等最新分选技术的原理与特点。最后,对现有雷达辐射源信号分选技术的不足进行了总结并对未来趋势进行了预测。