检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Usage: Uncertain Flow Graph and Spatio-Temporal Graph Network-Based Saturation Attack Detection Method

SSRN

引用

SSRN 2023年

作者： Wang, Kaixi Cui, Yunhe Qian, Qing Chen, Yi Guo, Chun Shen, Guowei Engineering Research Center of Text Computing & Cognitive Intelligence Guizhou University China State Key Laboratory of Public Big Data Guizhou University China Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guizhou University China College of Computer Science and Technology Guizhou University China School of Information Guizhou University of Finance and Economics China

With the development of software-Defined Networking (SDN), its security problems have become important research content. Among these security problems, saturation attack is one of the most destructive problems. Saturation attacks can destroy SDN networks. Currently, neural graph networks have already been used for detecting saturation attacks in SDN. When constructing the graph based on K-Nearest Neighbors (KNN) algorithm, the number of edges in the graph is fixed. That cannot reflect the different nodes’ relationship well. In addition, when using the Graph Convolutional Network (GCN) to detect saturation attack against SDN, only a partial graph structure and node features will be learned, causing the flow graph nodes information cannot be fully utilized. To overcome these issues, in this work, we propose USAGE, an uncertain flow graph and spatio-temporal graph network-based saturation attack detection method. More specifically, USAGE designs the CRAM algorithm and EGG model. The CRAM algorithm is designed to generate an uncertain flow graph for each traffic flow, which can represent the uncertain relationship among different nodes. EGG is a spatio-temporal graph convolutional network model, which is proposed to detect saturation attacks towards SDN switches. The evaluation results demonstrate that USAGE can generate a better graph than KNN and achieve high detection performance. Meanwhile, USAGE outperforms other methods in terms of TPR, TNR, accuracy, precision, recall, F-score, confusion matrix, ROC curves, and PR curves. © 2023, The Authors. All rights reserved.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

Detecting and Corrupting Convolution-based Unlearnable Examples

arXiv

引用

arXiv 2023年

作者： Li, Minghui Wang, Xianlong Yu, Zhifei Hu, Shengshan Zhou, Ziqi Zhang, Longling Zhang, Leo Yu School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms against UEs. The failure of such defenses can be attributed to the absence of norm constraints on convolutional noise, leading to severe blurring of image features. To address this, we first design an Edge Pixel-based Detector (EPD) to identify convolution-based UEs. Upon detection of them, we propose the first defense scheme against convolution-based UEs, COrrupting these samples via random matrix multiplication by employing bilinear INterpolation (COIN) such that disrupting the distribution of class-wise multiplicative noise. To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs. Extensive experiments demonstrate the effectiveness of detection scheme EPD and that our defense COIN outperforms 11 state-of-the-art (SOTA) defenses, achieving a significant improvement on the CIFAR and ImageNet datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Network for Recommendation 5

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Netw...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Tao, Li Xiaoge, Li Chaodong, Wang Xianliang, Li Shuai, Gao Dan, Han Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Computer Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China Inspur Software Technology Co Ltd Software Development Project Management China Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Communication and Information Engineering Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (纸本)9781450396899

It is commonly agreed that a recommender system based on knowledge graph (KG) should not only use user-item interactions, but also take side information into account to deal with the problem of data sparsity. However, existing KG-based models present unique challenges that have the shortcoming of cold start and redundant iterations. To address the issue, we propose a Feature Fusion-based Knowledge Graph Attention Network (FF-KGAT) for the recommendation. FF-KGAT handles the cold-start problem through introducing user characteristics to fully explore the information of users. Additionally, FF-KGAT introduces the feature fusion graph, which removes slight nodes to obtain fewer iterations. Experimental results show that the proposed model significantly outperforms baseline methods. Particularly, the ndcg is increased by 9.83% and 10.25% on two public datasets, compared with the best performance of existing methods. © 2022 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Towards Making More Reliable Cardiotocogram data Prediction with Limited Expert Knowledge: Exploiting Unlabeled data with Semi-supervised Boosting Method 6th

Towards Making More Reliable Cardiotocogram Data Prediction ...

引用

6th International Conference on data Mining and big data, DMBD 2021

作者： Hong, Jiaming Qin, Chen Huang, Yun Zhou, Yin School of Medical Information Engineering Guangzhou University of Chinese Medicine Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Software College Jishou University Zhangjiajie China School of Computer Science Shenzhen Institute of Information Technology Shenzhen China

ISBN: (纸本)9789811674754

Cardiotocography (CTG) is frequently used as a method of diagnosing fetal distress during pregnancy and delivery, including listening to Fetal Heart Rate (FHR) and monitoring Uterine Contractions (UC). Many scholars have contributed to classify CTG data through machine learning methods, intending to reduce the consuming-time and mistakes during obstetricians’ identification. In this study, we used repeated holdout cross-validation for data pre-processing and classified the CTG dataset as a normal class and pathological class. Sensitivity, specificity, accuracy, and AUC were involved to measure the performance of the models. According to the results of ASSEMBLE AdaBoost and AdaBoost, we can conclude that ASSEMBLE AdaBoost is robust in the classification of CTG data. Training with few labeled data and amounts of unlabeled data, ASSEMBLE AdaBoost achieved an accuracy of over 90%, which was superior to AdaBoost. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Debiased visual question answering from feature and sample perspectives 21

Debiased visual question answering from feature and sample p...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Zhiquan Wen Guanghui Xu Mingkui Tan Qingyao Wu Qi Wu School of Software Engineering South China University of Technology China and PengCheng Laboratory China School of Software Engineering South China University of Technology China School of Software Engineering South China University of Technology China and Key Laboratory of Big Data and Intelligent Robot (South China University of Technology) Ministry of Education School of Computer Science University of Adelaide

ISBN: (纸本)9781713845393

Visual question answering (VQA) is designed to examine the visual-textual reasoning ability of an intelligent agent. However, recent observations show that many VQA models may only capture the biases between questions and answers in a dataset rather than showing real reasoning abilities. For example, given a question, some VQA models tend to output the answer that occurs frequently in the dataset and ignore the images. To reduce this tendency, existing methods focus on weakening the language bias. Meanwhile, only a few works also consider vision bias implicitly. However, these methods introduce additional annotations or show unsatisfactory performance. Moreover, not all biases are harmful to the models. Some "biases" learnt from datasets represent natural rules of the world and can help limit the range of answers. Thus, how to filter and remove the true negative biases in language and vision modalities remain a major challenge. In this paper, we propose a method named D-VQA to alleviate the above challenges from the feature and sample perspectives. Specifically, from the feature perspective, we build a question-to-answer and vision-to-answer branch to capture the language and vision biases, respectively. Next, we apply two unimodal bias detection modules to explicitly recognise and remove the negative biases. From the sample perspective, we construct two types of negative samples to assist the training of the models, without introducing additional annotations. Extensive experiments on the VQA-CP v2 and VQA v2 datasets demonstrate the effectiveness of our D-VQA method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer-based stereo-aware 3D object detection from binocular images

arXiv

引用

arXiv 2023年

作者： Sun, Hanqing Pang, Yanwei Cao, Jiale Xie, Jin Li, Xuelong Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China Tianjin Key Laboratory of Brain-Inspired Intelligence Technology School of Electrical and Information Engineering Tianjin University Tianjin China School of Big Data and Software Engineering Chongqing University Chongqing China Northwestern Polytechnical University Xi’an China

Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed. © 2023, CC BY-NC-SA.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Exploring A CAM - Based Approach for Weakly Supervised Fire Detection Task

Exploring A CAM - Based Approach for Weakly Supervised Fire ...

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Lvlong Lai Jian Chen Huichou Huang Qingyao Wu School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education City University of Hong Kong Hong Kong China Pazhou Lab Guangzhou China

ISBN: (纸本)9781665444194

Most existing works in fire detection literature use available detectors like Faster RCNN, SSD, YOLO, etc. to localize the fire in images. These approaches work well but require object-level annotation for training, which is created manually and is very expensive. In this paper, we explore the weakly supervised fire detection task (WSFD) in which only the image-level annotation is given. We propose an approach based on class activation map (CAM). The CAM-based approach firstly trains a deep neural network as the classifier for identifying fire and non-fire images. For a fire image in the inference stage, it uses the classifier to create a CAM and then further generates the bounding boxes according to the CAM. To evaluate the effectiveness of our approach, we collect and construct a benchmark dataset named WS-FireNet and conduct comprehensive experiments on it. The experiment results show that in a way the performance of our approach is satisfactory.

关键词： Training Deep learning Annotations IEEE Sections Conferences Neural networks Detectors

来源：评论

学校读者我要写书评

暂无评论

Cooperative Sensing Via Matrix Factorization of the Partially Received Sample Covariance Matrix

Cooperative Sensing Via Matrix Factorization of the Partiall...

引用

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

作者： Rui Zhou Wenqiang Pu Licheng Zhao Ming-Yi You Qingjiang Shi Sergios Theodoridis Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China National Key Laboratory of Electromagnetic Space Security Jiaxing China School of Software Engineering Tongji University Shanghai China Department of Electronics Systems Aalborg University Denmark Department of Informatics and Telecommunications National and Kapodistrian University of Athens Greece

A fundamental problem in cognitive radio is spectrum sensing, which detects the presence of the primary users in a licensed spectrum. To boost the detection performance and robustness, the multiantenna detector has been investigated and various related methods have been developed, e.g., the energy detector, the eigenvalue arithmetic-to-geometric mean detector, and the generalized likelihood ratio test detector. Cooperative sensing, which makes use of multiple receivers distributed in different locations, has the advantage of being able to make full use of the distributed antennas and enjoy a high spatial diversity gain. However, the successful employment of cooperative sensing depends on the reliable information exchange among the cooperating receivers over a long range, which may be impractical for real-world scenarios. In this paper, we consider the scenario where each receiving node can only broadcast its received raw data in a short-range communication fashion. We propose a novel cooperative sensing scheme by allowing each node to send to the fusion center only local correlation coefficients, computed within a neighborhood. A detection algorithm, based on matrix factorization of the partially received sample covariance matrix, i.e., with missing entries, is proposed. The performance of our proposed cooperative scheme is verified via numerical experiments.

关键词：

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：