检索结果-内蒙古大学图书馆

DBSSL: A Scheme to Detect Backdoor Attacks in Self-Supervised Learning Models

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Huang, Yuxian Yang, Geng Yuan, Dong Yu, Shui Nanjing University of Posts and Telecommunication College of Computer Science and Software China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China University of Sydney School of Electrical and Information Engineering Australia University of Technology Sydney School of Computer Science Australia

Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significant threats to self-supervised learning. Additionally, due to the substantial training overhead, traditional backdoor detection methods in supervised learning, such as meta-learning, are not well-suited for self-supervised learning. Current backdoor detection methods for self-supervised learning can only defend against backdoor attacks triggered by patch. To address this challenge, we proposes DBSSL, a scheme that can efficiently detect backdoor attacks in self-supervised learning models. In DBSSL, we connect backdoor attacks with adversarial attacks and use adversarial perturbations for detection. Specifically, we first conduct targeted adversarial attacks on the samples, classifying them into different classes. Then, we employ the Z-Score method to analyze these adversarial perturbations. If outliers are present, we can infer that the self-supervised learning model has been backdoored. Unlike previous works, our scheme is better suited for downstream users with constrained computation resources and exhibits excellent detection capabilities for backdoor attacks caused by patch -type or global triggers. Abundant theoretical analysis has demonstrated the feasibility of our scheme. Moreover, extensive experiments show that our method performs well in detecting prevalent backdoor attacks in self-supervised learning, achieving detection accuracy exceeding 95%. © 2004-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hot-Start Transfer Learning Combined with Approximate Distillation for Mongolian-Chinese Neural Machine Translation 1

引用

18th China Conference on Machine Translation, CCMT 2022

作者： Wang, Pengcong Hou, Hongxu Sun, Shuo Wu, Nier Jian, Weichen Yang, Zongheng Wang, Yisong College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

When parallel training data is scarce, it will affect neural machine translation. For low-resource neural machine translation (NMT), transfer learning is very important, and the use of pre-training model can also alleviate the shortage of data. However, the good performance of common cold-start transfer learning methods is limited to the cognate language realized by sharing its vocabulary. Moreover, when using the pre-training model, the combination of general fine tuning methods and NMT will lead to a serious problem of knowledge forgetting. Both methods have some defects, so this paper optimizes the above two problems, and applies a new training framework suitable for low correlation language to Mongolian-Chinese neural machine translation. Our framework includes two technologies: a) word alignment method under hot-start, which alleviates the problem of word mismatch between the transferred subject and object in transfer learning. b) approximate distillation,not only retains the pre-trained knowledge, but also solves the forgetting problem, so that the encoder of NMT has stronger language representation ability. The results show that BLEU is increased by 3.2, which is better than ordinary transfer learning and multilingual translation system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Interactive Mongolian Question Answer Matching Model Based on Attention Mechanism in the Law Domain 21

Interactive Mongolian Question Answer Matching Model Based o...

引用

21st China National Conference on Computational Linguistics, CCL 2022

作者： Peng, Yutao Wang, Weihua Bao, Feilong College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9783031183140

Mongolian question answer matching task is challenging, since Mongolian is a kind of low-resource language and its complex morphological structures lead to data sparsity. In this work, we propose an Interactive Mongolian Question Answer Matching Model (IMQAMM) based on attention mechanism for Mongolian question answering system. The key parts of the model are interactive information enhancement and max-mean pooling matching. Interactive information enhancement contains sequence enhancement and multi-cast attention. Sequence enhancement aims to provide a subsequent encoder with an enhanced sequence representation, and multi-cast attention is designed to generate scalar features through multiple attention mechanisms. Max-Mean pooling matching is to obtain the matching vectors for aggregation. Moreover, we introduce Mongolian morpheme representation to better learn the semantic feature. The model experimented on the Mongolian corpus, which contains question-answer pairs of various categories in the law domain. Experimental results demonstrate that our proposed Mongolian question answer matching model significantly outperforms baseline models. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Multi-scale Framework for Out-of-Distribution Detection in Dermoscopic Images 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Zhongzheng Wang, Tao Cai, Yuanzheng Liang, Lingyu College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering and International Digital Economy College Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China Fujian Yilian-Health Nursing Information Technology Co. Ltd. Fuzhou350003 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

The automatic detection of skin diseases via dermoscopic images can improve the efficiency in diagnosis and help doctors make more accurate judgments. However, conventional skin disease recognition systems may produce high confidence for out-of-distribution (OOD) data, which may become a major security vulnerability in practical applications. In this paper, we propose a multi-scale detection framework to detect out-of-distribution skin disease image data to ensure the robustness of the system. Our framework extracts features from different layers of the neural network. In the early layers, rectified activation is used to make the output features closer to the well-behaved distribution, and then an one-class SVM is trained to detect OOD data;in the penultimate layer, an adapted Gram matrix is used to calculate the features after rectified activation, and finally the layer with the best performance is chosen to compute a normality score. Experiments show that the proposed framework achieves superior performance when compared with other state-of-the-art methods in the task of skin disease recognition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Event-based Video Person Re-identification via Cross-Modality and Temporal Collaboration

Event-based Video Person Re-identification via Cross-Modalit...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Renkai Li Xin Yuan Wei Liu Xin Xu School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Video-based person re-identification (ReID) has become increasingly important due to its applications in video surveillance applications. By employing events in video-based person ReID, more motion information can be provided between continuous frames to improve recognition accuracy. Previous approaches have assisted by introducing event data into the video person ReID task, but they still cannot avoid the privacy leakage problem caused by RGB images. In order to avoid privacy attacks and to take advantage of the benefits of event data, we consider using only event data. To make full use of the information in the event stream, we propose a Cross-Modality and Temporal Collaboration (CMTC) network for event-based video person ReID. First, we design an event transform network to obtain corresponding auxiliary information from the input of raw events. Additionally, we propose a differential modality collaboration module to balance the roles of events and auxiliaries to achieve complementary effects. Furthermore, we introduce a temporal collaboration module to exploit motion information and appearance cues. Experimental results demonstrate that our method outperforms others in the task of event-based video person ReID.

关键词： Data privacy Correlation Event detection Collaboration Transforms Streaming media Signal processing Video surveillance Speech processing Identification of persons

来源：评论

学校读者我要写书评

暂无评论

VAGeo: View-specific Attention for Cross-View Object Geo-Localization

VAGeo: View-specific Attention for Cross-View Object Geo-Loc...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhongyang Li Xin Yuan Wei Liu Xin Xu School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial correlation between the query image and the satellite-view reference image. To this end, this paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL. Specifically, VAGeo contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module. In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module. In feature-level, a hybrid attention in the CSHA module is introduced by combining channel attention and spatial attention mechanisms simultaneously for learning discriminative features. Extensive experimental results demonstrate that the proposed VAGeo gains a significant performance improvement, i.e., improving acc@0.25/acc@0.5 on the CVOGL dataset from 45.43%/42.24% to 48.21%/45.22% for ground-view, and from 61.97%/57.66% to 66.19%/61.87% for drone-view.

关键词： Location awareness Accuracy Attention mechanisms Image coding Signal processing Encoding Satellite images Object recognition Speech processing Drones

来源：评论

学校读者我要写书评

暂无评论

MFGB: Molecular Properties Prediction leveraging Self-supervised Morgan Fingerprint Representation Learning

MFGB: Molecular Properties Prediction leveraging Self-superv...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Fang, Shuyan Liu, Yu Liu, Song Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Prov. Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Wuhan University of Science and Technology Hubei Provincial Key Laboratory of Occupational Hazard Identification and Control Hubei Province Wuhan China

ISBN: (纸本)9798350337488

Simple molecular graphs or molecular line notations are insufficient for molecular representation learning models that automatically learn molecule representations to acquire deep semantic features about chemistry. Therefore, we proposed the Morgan Fingerprint Graph, a novel molecular graph model constructed with the nodes of the Morgan Fingerprint Identifier, whose nodes incorporate various properties of the atom neighborhood. Based on our Morgan Fingerprint Graph, we trained a BERT-based molecular representation model MFGB which employs a local rather than global attention module to adapt the model to the Morgan Fingerprint Graph. The attention module of MFGB regulates the exchange of information in the attention layer based on the connection information of the atoms in the molecules. To verify the effectiveness of MFGB, we selected several mainstream datasets for evaluation. The results demonstrated that our method improve the performance of molecular properties prediction. In addition, we analyzed MFGB from both the over-smoothing and the attention perspectives. The analysis indicates that the node vector representations learned from the Morgan Fingerprint Graph are generally less smoothing, and the attention distributions of MFGB match the partial charge density distribution of the molecules. © 2023 IEEE.

关键词： Molecular property prediction Molecular representation learning Morgan Fingerprint Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Hou, Junlin Xu, Jilan Xiao, Fan Zhang, Bo Xu, Yiqian Zhang, Yuejie Zou, Haidong Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopic Maculopathy is the leading cause of legal blindness in patients with pathologic myopia. Automated myopic maculopathy diagnosis is of vital importance to early treatment and progression slowdown. However, the scarcity of labeled fundus images with myopic maculopathy makes it challenging to improve diagnostic performance via deep learning models. In this paper, we construct a label-efficient deep learning framework for myopic maculopathy classification. In specific, we exploit two categories of pre-training methods, i.e., vision-language pre-training and self-supervised visual representation learning, to alleviate the overfitting problem caused by the limited number of training images. Moreover, we adopt a semi-supervised learning technique, namely pseudo labeling, to leverage a large number of unlabeled fundus images from external datasets. We also investigate the impact of other key components in model training for better performance, including backbone architecture, input resolution, and loss function. Our method is evaluated in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). Among 17 participating teams, our ensembled model ranked 1st on the leaderboard with an average score of 0.8752. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Approaches for Myopic Maculopathy Plus Lesions Segmentation 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Xiao, Fan Hou, Junlin Xu, Jilan Xu, Yiqian Zhang, Bo Zhang, Yuejie Zou, Haidong Feng, Rui Academy for Engineering and Technology Fudan University Shanghai China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopia is a leading cause of visual impairment and blindness in several countries. Effective diagnosis and intervention are crucial, typically relying on manual image analysis by ophthalmologists, which is time-consuming and experience-dependent. In this work, we introduce an ensemble of deep learning techniques for myopic maculopathy plus lesions segmentation. Specifically, we utilize UNet, UNet++, and DeeplabV3+ to segment three lesions with strong data augmentation. Our ensembled model has proved to be effective in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). This dataset covers classification, segmentation, and spherical equivalent prediction, fostering automated analysis research. Extensive experiments on the MMAC dataset reveal the superior performance of our proposed approach, which ranked 1st on the challenge leaderboard. This work addresses a critical need for accurate and efficient myopic maculopathy diagnosis and intervention. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：