A Gradient-Based Algorithm to Deceive Deep Neural Networks

Xie, Tianying; Li, Yantao

doi:10.1007/978-3-030-36808-1_7

Cited by 7 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the security of CNN is expected to be attached great importance. More precisely, researchers [171], [172], [173], [174] have proposed some methods to deceive CNN, resulting in a sharp drop in the accuracy. These methods can be classified into two categories: data poisoning and adversarial attacks.…”

Section: B Security Of Cnnmentioning

confidence: 99%

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Liu

Yang

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

2,080

544

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention both of industry and academia in the past few years. The existing reviews mainly focus on the applications of CNN in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide novel ideas and prospects in this fast-growing field as much as possible. Besides, not only two-dimensional convolution but also one-dimensional and multi-dimensional ones are involved. First, this review starts with a brief introduction to the history of CNN. Second, we provide an overview of CNN. Third, classic and advanced CNN models are introduced, especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for function selection. Fifth, the applications of onedimensional, two-dimensional, and multi-dimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed to serve as guidelines for future work.

show abstract

Section: B Security Of Cnnmentioning

confidence: 99%

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Liu

Yang

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

2,080

544

View full text Add to dashboard Cite

show abstract

“…2 (18) where n represents the parameters obtained through training in the VGG-16 network model. W d ðÁÞ represents the feature of the coherent layer of related features in the encoder, and W m ðÁÞ is the corresponding layer phase feature space of the relevant feature coherent layer in the decoder.…”

Section: Image Reconstruction and Loss Functionmentioning

confidence: 99%

“…The rapid development of deep learning methods has provided a new avenue for image reconstruction. [18][19][20] The image reconstruction method based on deep learning heavily trains the data of the database in a deep learning network, enabling the reconstruction model to learn more deep-level feature information of the image. As generative adversarial networks (GANs), which are regarded as an unsupervised deep learning model, are applied in the field of image reconstruction, [21][22][23] the image reconstruction has got further development.…”

Section: Introductionmentioning

confidence: 99%

Fine reconstruction of underwater images for environmental feature fusion

Zhou

Guo

et al. 2021

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Complicated underwater environments, such as occlusion by foreign objects and dim light, causes serious loss of underwater targets feature. Furthermore, underwater ripples cause target deformation, which greatly increases the difficulty of feature extraction. Then, existing image reconstruction models cannot effectively achieve target reconstruction due to insufficient underwater target features, and there is a blurred texture in the reconstructed area. To solve the above problems, a fine reconstruction of underwater images with the target feature missing from the environment feature was proposed. Firstly, the salient features of underwater images are obtained in terms of positive and negative sample learning. Secondly, a layered environmental attention mechanism is proposed to retrieve the relevant local and global features in the context. Finally, a coarse-to-fine image reconstruction model, with gradient penalty constraints, is constructed to obtain the fine restoration results. Contrast experiment between the proposed algorithm and the existing image reconstruction methods has been done in stereo quantitative underwater image data set, real-world underwater image enhancement data set, and underwater image data set, clearly proving that the proposed one is more effective and superior.

show abstract

“…For instance, Xu et al [24] introduce the semantic loss that augments the training objective of neural networks with soft-constraints specified with domain knowledge; Allamanis et al [25] propose to learn continuous representations of symbolic knowledge for integration into neural networks. On the application side, neural-symbolic methods have been applied to both vision and language tasks including visual relation prediction [26], visual question answering (VQA) [27], text sentiment analysis [28], and semantic parsing [29].…”

Section: Introductionmentioning

confidence: 99%

Learning from Noisy Crowd Labels with Logics

Chen¹,

Sun²,

He³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper explores the integration of symbolic logic knowledge into deep neural networks for learning from noisy crowd labels. We introduce Logic-guided Learning from Noisy Crowd Labels (Logic-LNCL), an EM-alike iterative logic knowledge distillation framework that learns from both noisy labeled data and logic rules of interest. Unlike traditional EM methods, our framework contains a "pseudo-E-step" that distills from the logic rules a new type of learning target, which is then used in the "pseudo-M-step" for training the classifier. Extensive evaluations on two real-world datasets for text sentiment classification and named entity recognition demonstrate that the proposed framework improves the state-of-the-art and provides a new solution to learning from noisy crowd labels.

show abstract

A Gradient-Based Algorithm to Deceive Deep Neural Networks

Cited by 7 publications

References 16 publications

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Fine reconstruction of underwater images for environmental feature fusion

Learning from Noisy Crowd Labels with Logics

Contact Info

Product

Resources

About