Search scope:
排序: Display mode:
Adversarial Attacks and Defenses in Deep Learning Feature Article
Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu
Engineering 2020, Volume 6, Issue 3, Pages 346-360 doi: 10.1016/j.eng.2019.12.012
With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques, it is critical
to ensure the security and robustness of the deployed algorithms. Recently, the security vulnerability of
DL algorithms to adversarial samples has been widely recognized. The fabricated samples can lead to various
misbehaviors of the DL models while being perceived as benign by humans. Successful implementations
of adversarial attacks in real physical-world scenarios further demonstrate their practicality.
Hence, adversarial attack and defense techniques have attracted increasing attention from both machine
learning and security communities and have become a hot research topic in recent years. In this paper,
we first introduce the theoretical foundations, algorithms, and applications of adversarial attack techniques.
We then describe a few research efforts on the defense techniques, which cover the broad frontier
in the field. Several open problems and challenges are subsequently discussed, which we hope will provoke
further research efforts in this critical area.
Keywords: Machine learning Deep neural network Adversarial example Adversarial attack Adversarial defense
Neuromorphic Computing Advances Deep-Learning Applications
Chris Palmer
Engineering 2020, Volume 6, Issue 8, Pages 854-856 doi: 10.1016/j.eng.2020.06.010
Visual interpretability for deep learning: a survey Review
Quan-shi ZHANG, Song-chun ZHU
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1, Pages 27-39 doi: 10.1631/FITEE.1700808
Keywords: Artificial intelligence Deep learning Interpretable model
Mingzhi Zhao, Huiliang Wei, Yiming Mao, Changdong Zhang, Tingting Liu, Wenhe Liao
Engineering 2023, Volume 23, Issue 4, Pages 181-195 doi: 10.1016/j.eng.2022.09.015
Molten pool characteristics have a significant effect on printing quality in laser powder bed fusion (PBF), and quantitative predictions of printing parameters and molten pool dimensions are critical to the intelligent control of the complex processes in PBF. Thus far, bidirectional predictions of printing parameters and molten pool dimensions have been challenging due to the highly nonlinear correlations involved. To
address this issue, we integrate an experiment on molten pool characteristics, a mechanistic model, and deep learning to achieve both forward and inverse predictions of key parameters and molten pool characteristics during laser PBF. The experiment provides fundamental data, the mechanistic model significantly augments the dataset, and the multilayer perceptron (MLP) deep learning model predicts the molten pool dimensions and process parameters based on the dataset built from the experiment and the mechanistic model. The results show that bidirectional predictions of the molten pool dimensions and process parameters can be realized, with the highest prediction accuracies approaching 99.9% and mean prediction accuracies of over 90.0%. Moreover, the prediction accuracy of the MLP model is closely related to the characteristics of the dataset—that is, the learnability of the dataset has a crucial impact on the prediction accuracy. The highest prediction accuracy is 97.3% with enhancement of the dataset via the mechanistic model, while the highest prediction accuracy is 68.3% when using only the experimental dataset. The prediction accuracy of the MLP model largely depends on the quality of the dataset as well. The research results demonstrate that bidirectional predictions of complex correlations using MLP are feasible for laser PBF, and offer a novel and useful framework for the determination of process conditions and outcomes for intelligent additive manufacturing.
Keywords: Additive manufacturing Molten pool Model Deep learning Learnability
Robust object tracking with RGBD-based sparse learning Article
Zi-ang MA, Zhi-yu XIANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 7, Pages 989-1001 doi: 10.1631/FITEE.1601338
Keywords: Object tracking Sparse learning Depth view Occlusion templates Occlusion detection
Disambiguating named entitieswith deep supervised learning via crowd labels Article
Le-kui ZHOU,Si-liang TANG,Jun XIAO,Fei WU,Yue-ting ZHUANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 1, Pages 97-106 doi: 10.1631/FITEE.1601835
Keywords: Named entity disambiguation Crowdsourcing Deep learning
Estimating Rainfall Intensity Using an Image-Based Deep Learning Model Article
Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan
Engineering 2023, Volume 21, Issue 2, Pages 162-174 doi: 10.1016/j.eng.2021.11.021
Urban flooding is a major issue worldwide, causing huge economic losses and serious threats to public safety. One promising way to mitigate its impacts is to develop a real-time flood risk management system; however, building such a system is often challenging due to the lack of high spatiotemporal rainfall data. While some approaches (i.e., ground rainfall stations or radar and satellite techniques) are available to measure and/or predict rainfall intensity, it is difficult to obtain accurate rainfall data with a desirable spatiotemporal resolution using these methods. This paper proposes an image-based deep learning model to estimate urban rainfall intensity with high spatial and temporal resolution. More specifically, a convolutional neural network (CNN) model called the image-based rainfall CNN (irCNN) model is developed using rainfall images collected from existing dense sensors (i.e., smart phones or transportation cameras) and their corresponding measured rainfall intensity values. The trained irCNN model is subsequently employed to efficiently estimate rainfall intensity based on the sensors' rainfall images. Synthetic rainfall data and real rainfall images are respectively utilized to explore the irCNN's accuracy in theoretically and practically simulating rainfall intensity. The results show that the irCNN model provides rainfall estimates with a mean absolute percentage error ranging between 13.5% and 21.9%, which exceeds the performance of other state-of-the-art modeling techniques in the literature. More importantly, the main feature of the proposed irCNN is its low cost in efficiently acquiring high spatiotemporal urban rainfall data. The irCNN model provides a promising alternative for estimating urban rainfall intensity, which can greatly facilitate the development of urban flood risk management in a real-time manner.
Keywords: Urban flooding Rainfall images Deep learning model Convolutional neural networks (CNNs) Rainfall intensity
Diffractive Deep Neural Networks at Visible Wavelengths Article
Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin
Engineering 2021, Volume 7, Issue 10, Pages 1485-1493 doi: 10.1016/j.eng.2020.07.032
Optical deep learning based on diffractive optical elements offers unique advantages for parallel processing, computational speed, and power efficiency. One landmark method is the diffractive deep neural network (D2NN) based on three-dimensional printing technology operated in the terahertz spectral range. Since the terahertz bandwidth involves limited interparticle coupling and material losses, this paper
extends D2NN to visible wavelengths. A general theory including a revised formula is proposed to solve any contradictions between wavelength, neuron size, and fabrication limitations. A novel visible light D2NN classifier is used to recognize unchanged targets (handwritten digits ranging from 0 to 9) and targets that have been changed (i.e., targets that have been covered or altered) at a visible wavelength of 632.8 nm. The obtained experimental classification accuracy (84%) and numerical classification accuracy (91.57%) quantify the match between the theoretical design and fabricated system performance. The presented framework can be used to apply a D2NN to various practical applications and design other new applications.
Keywords: Optical computation Optical neural networks Deep learning Optical machine learning Diffractive deep neural networks
A Geometric Understanding of Deep Learning Article
Na Lei, Dongsheng An, Yang Guo, Kehua Su, Shixia Liu, Zhongxuan Luo, Shing-Tung Yau, Xianfeng Gu
Engineering 2020, Volume 6, Issue 3, Pages 361-374 doi: 10.1016/j.eng.2019.09.010
This work introduces an optimal transportation (OT) view of generative adversarial networks (GANs). Natural datasets have intrinsic patterns, which can be summarized as the manifold distribution principle: the distribution of a class of data is close to a low-dimensional manifold. GANs mainly accomplish two tasks: manifold learning and probability distribution transformation. The latter can be carried out using the classical OT method. From the OT perspective, the generator computes the OT map, while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution; both can be reduced to a convex geometric optimization process. Furthermore, OT theory discovers the intrinsic collaborative—instead of competitive—relation between the generator and the discriminator, and the fundamental reason for mode collapse. We also propose a novel generative model, which uses an autoencoder (AE) for manifold learning and OT map for probability distribution transformation. This AE–OT model improves the theoretical rigor and transparency, as well as the computational stability and efficiency; in particular, it eliminates the mode collapse. The experimental results validate our hypothesis, and demonstrate the advantages of our proposed model.
Keywords: Generative Adversarial Deep learning Optimal transportation Mode collapse
Smart grid dispatch powered by deep learning: a survey Review Article
Gang HUANG, Fei WU, Chuangxin GUO,huanggang@zju.edu.cn,wufei@zju.edu.cn,guochuangxin@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 5, Pages 763-776 doi: 10.1631/FITEE.2000719
Keywords: Artificial intelligence Deep learning Power dispatch Smart grid
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis Article
Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao
Engineering 2021, Volume 7, Issue 7, Pages 1002-1010 doi: 10.1016/j.eng.2020.04.012
Infectious keratitis is the most common condition of corneal diseases in which a pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues. Infectious keratitis is a medical emergency for which a rapid and accurate diagnosis is needed to ensure prompt and precise treatment to halt the disease progression and to limit the extent of corneal damage; otherwise, it may develop a sight threatening and even eye-globe-threatening condition. In this paper, we propose a sequentiallevel deep model to effectively discriminate infectious corneal disease via the classification of clinical images. In this approach, we devise an appropriate mechanism to preserve the spatial structures of clinical images and disentangle the informative features for clinical image classification of infectious keratitis. In a comparison, the performance of the proposed sequential-level deep model achieved 80% diagnostic accuracy, far better than the 49.27% ± 11.5% diagnostic accuracy achieved by 421 ophthalmologists over 120 test images.
Keywords: Deep learning Corneal disease Sequential features Machine learning Long short-term memory
Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain Article
Qianyun Zhang,Kaveh Barri,Saeed K. Babanajad,Amir H. Alavi
Engineering 2021, Volume 7, Issue 12, Pages 1786-1796 doi: 10.1016/j.eng.2020.07.026
This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network (1D-CNN) and long short-term memory (LSTM) method in the image frequency domain. The so-called 1D-CNN-LSTM algorithm is trained using thousands of images of cracked and non-cracked concrete bridge decks. In order to improve the training efficiency, images are first transformed into the frequency domain during a preprocessing phase. The algorithm is then calibrated using the flattened frequency data. LSTM is used to improve the performance of the developed network for long sequence data. The accuracy of the developed model is 99.05%, 98.9%, and 99.25%, respectively, for training, validation, and testing data. An implementation framework is further developed for future application of the trained model for large-scale images. The proposed 1D-CNN-LSTM method exhibits superior performance in comparison with existing deep learning methods in terms of accuracy and computation time. The fast implementation of the 1D-CNN-LSTM algorithm makes it a promising tool for real-time crack detection.
Keywords: Crack detection Concrete bridge deck Deep learning Real-time
Deep Learning and Industrial Internet Security: Application and Challenges
Yang Chen, Ma Ruicheng, Wang Yushi, Zhai Yanlong, Zhu Liehuang
Strategic Study of CAE 2021, Volume 23, Issue 2, Pages 95-103 doi: 10.15302/J-SSCAE-2021.02.013
Industrial Internet security is crucial for strengthening the manufacturing and network sectors of China. Deep learning, owing to its strong expression ability, good adaptability, and high portability, can support the establishment of an industrial Internet security system and method that is intelligent and autonomous. Therefore, it is of great value to promote the integrated innovation of deep learning and industrial Internet security. In this study, we analyze the development demand for industrial Internet security from the perspective of macro industrial environment, security technology, and deep learning system, and summarize the application status of deep learning to industrial Internet security in terms of device, control, network, application, and data layers. The security challenges faced by deep learning application to industrial Internet security primarily lie in model training and prediction, and key research directions include interpretability of deep neural networks, cost control of sample collection and calculation, imbalance of sample sets, reliability of model results, tradeoff between availability and security. Furthermore, some suggestion are proposed: a dynamic defense system in depth should be established in terms of overall security strategy; an application-driven and frontier exploration integrated method should be adopted to achieve breakthroughs regarding key technologies; and resources input should be raised for interdisciplinary fields to establish an industry–university–research institute joint research ecosystem.
Keywords: industrial Internet security Internet of Things security deep learning data security
Jingda Wu, Zhiyu Huang, Zhongxu Hu, Chen Lv
Engineering 2023, Volume 21, Issue 2, Pages 75-91 doi: 10.1016/j.eng.2022.05.017
Due to its limited intelligence and abilities, machine learning is currently unable to handle various situations thus cannot completely replace humans in real-world applications. Because humans exhibit robustness and adaptability in complex scenarios, it is crucial to introduce humans into the training loop of artificial intelligence (AI), leveraging human intelligence to further advance machine learning algorithms. In this study, a real-time human-guidance-based (Hug)-deep reinforcement learning (DRL) method is developed for policy training in an end-to-end autonomous driving case. With our newly designed mechanism for control transfer between humans and automation, humans are able to intervene and correct the agent's unreasonable actions in real time when necessary during the model training process. Based on this human-in-the-loop guidance mechanism, an improved actor-critic architecture with modified policy and value networks is developed. The fast convergence of the proposed Hug-DRL allows real-time human guidance actions to be fused into the agent's training loop, further improving the efficiency and performance of DRL. The developed method is validated by human-in-the-loop experiments with 40 subjects and compared with other state-of-the-art learning approaches. The results suggest that the proposed method can effectively enhance the training efficiency and performance of the DRL algorithm under human guidance without imposing specific requirements on participants' expertise or experience.
Keywords: Human-in-the-loop AI Deep reinforcement learning Human guidance Autonomous driving
A review of computer graphics approaches to urban modeling from a machine learning perspective Review Article
Tian Feng, Feiyi Fan, Tomasz Bednarz,t.feng@latrobe.edu.au
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 7, Pages 915-925 doi: 10.1631/FITEE.2000141
Keywords: 城市建模;计算机图形学;机器学习;深度学习
Title Author Date Type Operation
Adversarial Attacks and Defenses in Deep Learning
Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu
Journal Article
Predictions of Additive Manufacturing Process Parameters and Molten Pool Dimensions with a Physics-Informed Deep Learning Model
Mingzhi Zhao, Huiliang Wei, Yiming Mao, Changdong Zhang, Tingting Liu, Wenhe Liao
Journal Article
Disambiguating named entitieswith deep supervised learning via crowd labels
Le-kui ZHOU,Si-liang TANG,Jun XIAO,Fei WU,Yue-ting ZHUANG
Journal Article
Estimating Rainfall Intensity Using an Image-Based Deep Learning Model
Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan
Journal Article
Diffractive Deep Neural Networks at Visible Wavelengths
Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin
Journal Article
A Geometric Understanding of Deep Learning
Na Lei, Dongsheng An, Yang Guo, Kehua Su, Shixia Liu, Zhongxuan Luo, Shing-Tung Yau, Xianfeng Gu
Journal Article
Smart grid dispatch powered by deep learning: a survey
Gang HUANG, Fei WU, Chuangxin GUO,huanggang@zju.edu.cn,wufei@zju.edu.cn,guochuangxin@zju.edu.cn
Journal Article
Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis
Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao
Journal Article
Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain
Qianyun Zhang,Kaveh Barri,Saeed K. Babanajad,Amir H. Alavi
Journal Article
Deep Learning and Industrial Internet Security: Application and Challenges
Yang Chen, Ma Ruicheng, Wang Yushi, Zhai Yanlong, Zhu Liehuang
Journal Article
Toward Human-in-the-loop AI: Enhancing Deep Reinforcement Learning Via Real-time Human Guidance for Autonomous Driving
Jingda Wu, Zhiyu Huang, Zhongxu Hu, Chen Lv
Journal Article