检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chenxi Zheng Bangzhen Liu Huaidong Zhang Xuemiao Xu Shengfeng He South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Singapore Management University

Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to the novel category, and therefore introduce two latent subspace optimization objectives. In the first one we use few-shot samples as positive anchors of the novel class, and adjust the StyleGAN to produce the corresponding results with the new class label condition. The second objective is to govern the generation process from the other way around, by altering the centroid and its surrounding latent subspace for a more precise generation of the novel class. These reciprocal optimization objectives inject a novel class into the StyleGAN latent subspace, and therefore new unseen samples can be easily produced by sampling images from it. Extensive experiments demonstrate superior few-shot generation performances compared with state-of-the-art methods, especially in terms of diversity and generation quality. Code is available at https://***/chansey0529/LSO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PM$^{2}$2VE: Power Metering Model for Virtualization Environments in Cloud data Centers

引用

IEEE Transactions on Cloud Computing 2023年第3期11卷 3126-3138页

作者： Ziyu Shen Xusheng Zhang Zheng Liu Yun Li School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory for Big Data Security and Intelligent Processing School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

Virtualization technologies provide solutions for cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many practical models for estimating the power consumption of virtual machines (VMs) have been proposed, few power estimation models of containers have been put forth. In this article, we propose a fast-training piecewise regression model based on a decision tree for VM power metering and estimate the power of containers configured on the VM by treating the container as a group of processes on the VM. We select appropriate features from the collected metrics of VMs/containers to help our model fit the nonlinear relationship between power and features well. Besides, we optimize the leaf nodes of the regression tree, realizing the effective power metering of virtualization environments. We evaluate the proposed model on 13 tasks in PARSEC and compare it with several commonly used models in data centers. The experimental results prove the effectiveness of the proposed model, and the estimated power of containers is in line with expectations.

关键词： Containers data centers Power demand Estimation data models Virtualization Servers

来源：评论

学校读者我要写书评

暂无评论

SCALABLE ATTRIBUTION OF ADVERSARIAL ATTACKS VIA MULTI-TASK LEARNING

arXiv

引用

arXiv 2023年

作者： Guo, Zhongyi Han, Keji Ge, Yao Ji, Wei Li, Yun Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversarial examples. Many works focus on adversarial detection and adversarial training to defend against adversarial attacks. However, few works explore the tool-chains behind adversarial examples, which can help defenders to seize the clues about the originator of the attack, their goals, and provide insight into the most effective defense algorithm against corresponding attacks. With such a gap, it is necessary to develop techniques that can recognize tool-chains that are leveraged to generate the adversarial examples, which is called Adversarial Attribution Problem (AAP). In this paper, AAP is defined as the recognition of three signatures, i.e., attack algorithm, victim model and hyperparameter. Current works transfer AAP into single label classification task and ignore the relationship between these signatures. The former will meet combination explosion problem as the number of signatures is increasing. The latter dictates that we cannot treat AAP simply as a single task problem. We first conduct some experiments to validate the attributability of adversarial examples. Furthermore, we propose a multi-task learning framework named Multi-Task Adversarial Attribution (MTAA) to recognize the three signatures simultaneously. MTAA contains perturbation extraction module, adversarial-only extraction module and classification and regression module. It takes the relationship between attack algorithm and corresponding hyperparameter into account and uses the uncertainty weighted loss to adjust the weights of three recognition tasks. The experimental results on MNIST and ImageNet show the feasibility and scalability of the proposed framework as well as its effectiveness in dealing with false alarms. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustness May be at Odds with Stability in Adversarial Training based Feature Selection?

Robustness May be at Odds with Stability in Adversarial Trai...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yue Liu Yun Li Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

As an important stage in machine learning pipeline, feature selection techniques are mainly used to improve the generalization performance and training efficiency of machine learning model, but few works have focused on the robustness of machine learning models from the perspective of feature selection when dealing with adversarial attacks. In this paper, we propose the adversarial training (AT) based feature selection framework, i.e. AT based feature selection, to improve the robustness of machine learning model built on the feature selection result, which is inspired by using adversarial training to improve the robustness of deep learning model. AT based feature selection framework is the combination of adversarial training with some traditional feature selection algorithm, which can be divided into AT in-processing and AT post-processing feature selection. On the other hand, stability is also a very important property for feature selection. Then we experimentally analyze the relationship between robustness and stability of AT based feature selection, especially theoretically analyze the stability of $\ell_{2}$ regularized AT in-processing feature selection algorithm in two different adversarial training forms. Our experimental results on benchmark data sets show that AT based feature selection algorithm is effective to improve the robustness of machine learning model, however, obtain lower stability than corresponding feature selection model without AT.

关键词： Training Deep learning Machine learning algorithms Pipelines Benchmark testing Feature extraction Stability analysis

来源：评论

学校读者我要写书评

暂无评论

LogPal: A Generic Anomaly Detection Scheme of Heterogeneous Logs for Network Systems

引用

security and Communication Networks 2023年第1期2023卷

作者： Sun, Lei Xu, Xiaolong Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China

As a key resource for diagnosing and identifying problems, network syslog contains vast quantities of information. And it is the main source of data for anomaly detection of systems. Syslog presents the characteristics of large scale, diverse types and sources, data noise, and quick evolvement, which makes the detection methods not generic enough. To effectively address problem of log anomaly labelling caused by massive heterogeneous logs, we propose LogPal, a generic anomaly detection scheme of heterogeneous logs for network systems, which innovatively combines template sequences and raw log sequences to construct and generate log pattern events. By improving the self-attention mechanism of transformer, LogPal proactively synthesizes self-attention and handles log pattern events in a unique way. The model can make full use of log template and sequence semantic information, by automatically becoming aware of the pattern of logs. We implemented experiments to evaluate the performance of LogPal on publicly available datasets, and the outcome of the experiments shows that LogPal automatically adapts to log type changes and improves precision, recall, and F1 score to 99% on publicly available datasets. © 2023 Lei Sun and Xiaolong Xu.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Rough Shadowed Set: Hybridization of Rough Set and Shadowed Set 11th

Rough Shadowed Set: Hybridization of Rough Set and Shadowe...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Gao, Man Zhang, Qinghua Jin, Pengren Xia, Deyou Wang, Guoyin School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing 400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing 400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing 401331 China

ISBN: (纸本)9783031927461

Shadowed set is a mathematical tool that processes uncertain information through three-way approximations, effectively reducing the cost of fuzzy decision-making and computation, and has been widely used in fields such as data mining, pattern recognition, and decision support. However, the existing shadowed set models are mainly based on the consideration of a single fuzzy set, lacking the comprehensive consideration of multiple fuzzy sets (multiple attributes, multiple approximation spaces) and information granules (equivalent classes), which is difficult to effectively achieve the approximate description of complex target concepts. In addition, the issues of “hard computation” and “subjectivity” in traditional rough set models also weaken the effectiveness of the three-way partitioning results. Therefore, Rough Shadowed Set (RSS) is proposed in this paper. First, analyzed the mapping relationship between rough set, shadowed set, and the three-way decision, and divided the results of the approximate partitioning of RSS into two stages. Second, in two stages, rough set is utilized to achieve comprehensive consideration of multiple attributes and information granules, shadowed set is utilized to achieve deblurring of real valued information system, and quadratic analysis and partitioning of uncertainty equivalence classes in the boundary region of rough set. Third, integrating the results of two stages to achieve the combination of the advantages of rough set and shadowed set theory, as well as a more reasonable and effective approximation of complex target concepts. Finally, the framework, definition, decision rules, algorithms, experimental analysis, and future discussions of the model are presented. The experimental results indicate that RSS has better payoff compared to traditional rough set and shadowed set models, namely higher approximate coverage and accuracy, which demonstrates the validity and rationality of RSS. © The Author(s), under exclusive license to

关键词： Fuzzy set Granular computing Rough set Shadowed set Three-way approximation

来源：评论

学校读者我要写书评

暂无评论

MNN: Mixed Nearest-Neighbors for Self-Supervised Learning

arXiv

引用

arXiv 2023年

作者： Long, Xianzhong Peng, Chen Li, Yun School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China

In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is to incorporate the relationship between samples, which involves including the top-K nearest neighbors of positive samples. However, the problem of false neighbors (i.e., neighbors that do not belong to the same category as the positive sample) is an objective but often overlooked challenge due to the query of neighbor samples without supervision information. In this paper, we present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN). MNN optimizes the influence of neighbor samples on the semantics of positive samples through an intuitive weighting approach and image mixture operations. The results demonstrate that MNN exhibits exceptional generalization performance and training efficiency on four benchmark datasets. © 2023, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Provably Secure Certificateless Signature Scheme With Anonymity for Healthcare IIoT

引用

IEEE Internet of Things Journal 2025年

作者： Qiao, Zirui Xu, Ran Zhou, Yanwei Yang, Bo Zhu, Tianqing Zhang, Mingwu Xi’an University of Posts and Telecommunications School of Cyberspace Security Xi’an China Ministry of Education Key Laboratory of Data Protection and Intelligent Management China Shaanxi Normal University School of Computer Science Xi’an China City University of Macau Faculty of Data Science Macau China Hubei University of Technology School of Computer Wuhan China

The industrial Internet of Things (IIoT) is changing our way of life and work. As the number of mobile devices connected to IIoT increases, users will face many security challenges such as insecure communication environments. The certificateless signature (CLS) scheme can ensure the integrity and validity of data and provide secure identity authentication for the IIoT, and several pairing-free CLS schemes have been proposed in recent years. However, we find they are vulnerable to the signature forgery attack of malicious key generation centers by safety analysis, which does not realize the security they have claimed. To solve this problem, we show an improved CLS scheme that achieves anonymity and formally proves its security under the hardness of the discrete logarithm problem in the random oracle. Comprehensive performance analysis and comparison show that our scheme has less communication and computation costs with higher security, and our construction is suitable for scenarios with limited resources. Finally, we apply this scheme to construct a mutual identity authentication protocol in the healthcare IIoT environment. 2014 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Dafl: Domain Adaptation-Based Federated Learning for Privacy-Preserving Biometric Recognition

SSRN

引用

SSRN 2023年

作者： Wang, Zhousheng Yang, Geng Dai, Hua Bai, Yunlu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big data Security & Intelligent Processing Nanjing210023 China

With the introduction of data protection regulation in various countries, traditional centralized learning for the exploitation of sensitive biological information will gradually become unsustainable. We take face and speaker recognition systems as examples, to consider the possibility of implementing them using federated learning. It is known that federated learning methods still have some issues to be solved, e.g., parameter updates delivered can still reveal user privacy. Besides, existing privacy-preserving methods such as encryption and perturbation could pose other problems, including low accuracy and high training overhead, which can be more prominent in biometric recognition scenarios. We adopt the idea of domain adaptation and propose a new federated learning framework, DAFL, focusing on the improvement of the training efficiency and model performance, to achieve a practical privacy-preserving biometric recognition scheme for the first time. We also design a special dropout method for it to address the possible imbalance of biometric samples across users. Experiments on real-world datasets show that our approach can achieve up to 95.6% and 97.9% accuracy in face recognition and speaker recognition tasks, respectively, under medium privacy settings. Compared with existing work, it can save 56.0% of training time with a 3.1% accuracy loss in the best case. © 2023, The Authors. All rights reserved.

关键词： Biometrics

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：