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

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

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

Dynamic Residual Classifier for Class Incremental Learning

arXiv

引用

arXiv 2023年

作者： Chen, Xiuwei Chang, Xiaobin School of Artificial Intelligence Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Region Enhanced Discrete Multi-Objective Fireworks Algorithm for Low-Carbon Vehicle Routing Problem

引用

Complex System Modeling and Simulation 2022年第2期2卷 142-155页

作者： Xiaoning Shen Jiaqi Lu Xuan You Liyan Song Zhongpei Ge Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Jiangsu Key Laboratory of Big Data Analysis TechnologySchool of AutomationNanjing University of Information Science and TechnologyNanjing 210044China School of Automation Nanjing University of Information Science and TechnologyNanjing 210044China Institute of Trustworthy Autonomous Systems and also with the Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent ComputationDepartment of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

A constrained multi-objective optimization model for the low-carbon vehicle routing problem(VRP)is established.A carbon emission measurement method considering various practical factors is *** minimizes both the total carbon emissions and the longest time consumed by the sub-tours,subject to the limited number of available *** to the characteristics of the model,a region enhanced discrete multi-objective fireworks algorithm is proposed.A partial mapping explosion operator,a hybrid mutation for adjusting the sub-tours,and an objective-driven extending search are designed,which aim to improve the convergence,diversity,and spread of the non-dominated solutions produced by the algorithm,*** low-carbon VRP instances with different scales are used to verify the effectiveness of the new ***,comparison results with four state-of-the-art algorithms indicate that the proposed algorithm has better performance of convergence and distribution on the low-carbon *** provides a promising scalability to the problem size.

关键词： vehicle routing problem carbon emission multi-objective optimization fireworks algorithm region enhanced

来源：评论

学校读者我要写书评

暂无评论

Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysis

arXiv

引用

arXiv 2023年

作者： Chen, Xiuwei Chang, Xiaobin School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Class incremental learning (CIL) aims to recognize both the old and new classes along the increment tasks. Deep neural networks in CIL suffer from catastrophic forgetting and some approaches rely on saving exemplars from previous tasks, known as the exemplar-based setting, to alleviate this problem. On the contrary, this paper focuses on the Exemplar-Free setting with no old class sample preserved. Balancing the plasticity and stability in deep feature learning with only supervision from new classes is more challenging. Most existing Exemplar-Free CIL methods report the overall performance only and lack further analysis. In this work, different methods are examined with complementary metrics in greater detail. Moreover, we propose a simple CIL method, Rotation Augmented Distillation (RAD), which achieves one of the top-tier performances under the Exemplar-Free setting. Detailed analysis shows our RAD benefits from the superior balance between plasticity and stability. Finally, more challenging exemplar-free settings with fewer initial classes are undertaken for further demonstrations and comparisons among the state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

4K-Resolution Photo Exposure Correction at 125 FPS with ∼8K Parameters

arXiv

引用

arXiv 2023年

作者： Zhou, Yijie Li, Chao Liang, Jin Xu, Tianyi Liu, Xin Xu, Jun Nankai University China Tianjin University China Lappeenranta-Lahti University of Technology Finland Guangdong Provincial Key Laboratory of Big Data Computing CUHK Shenzhen China

The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers. Despite with promising performance, these methods usually suffer from large parameter amounts and heavy computational FLOPs on high-resolution photographs. In this paper, we propose extremely light-weight (with only ∼8K parameters) Multi-Scale Linear Transformation (MSLT) networks under the multi-layer perception architecture, which can process 4K-resolution sRGB images at 125 Frame-Per-Second (FPS) by a Titan RTX GPU. Specifically, the proposed MSLT networks first decompose an input image into high and low frequency layers by Laplacian pyramid techniques, and then sequentially correct different layers by pixel-adaptive linear transformation, which is implemented by efficient bilateral grid learning or 1 × 1 convolutions. Experiments on two benchmark datasets demonstrate the efficiency of our MSLTs against the state-of-the-arts on photo exposure correction. Extensive ablation studies validate the effectiveness of our contributions. The code is available at https://***/Zhou-Yijie/MSLTNet. 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

Ascl: Accelerating Semi-Supervised Learning Via Contrastive Learning

SSRN

引用

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Is Really Correlation Information Represented Well in Self-Attention for Skeleton-based Action Recognition?

Is Really Correlation Information Represented Well in Self-A...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wentian Xin Hongkai Lin Ruyi Liu Yi Liu Qiguang Miao School of Computer Science and Technology Xidian University China Xi’an Key Laboratory of Big Data and Intelligent Vision Xidian University China Ministry of Education Key Laboratory of Collaborative Intelligence Systems Xidian University China

Transformer has shown significant advantages by various vision tasks. However, the lack of representation of correlation information about data properties makes it difficult to match the excellent results consistent with GCNs in skeleton-based action recognition. In this paper, we propose a Topology and Frames-guided Spatial-Temporal ConvFormer Network (TF-STCFormer), which is well suited for dynamically extracting topological and inter-frame uniqueness & co-occurrence information. Three essential components make up the proposed framework: (1) Grouped Physical-guided Spatial Transformer for focusing on learning essential spatial features and physical topology. (2) Global and Focal Temporal Transformer for promoting the relationship of different joints in consecutive frames and improving the representation of discriminative key-frames. (3) Grouped Dilation Temporal Convolution for connecting the intermediate output obtained by the previous transformers in the feature channels of different dilation. Experiments on four standard datasets (NTU RGB+D, NTU RGB+D 120, NW-UCLA, and UAV-Human) demonstrate that our approach prominently outperforms state-of-the-art methods on all benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A robust three-way classifier with shadowed granular-balls based on justifiable granularity

arXiv

引用

arXiv 2024年

作者： Yang, Jie Xiaodiao, Lingyun Wang, Guoyin Pedrycz, Witold Xia, Shuyin Zhang, Qinghua Wu, Di The Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China The School of Physics and Electronic Science Zunyi Normal University Zunyi563002 China The Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Chongqing400065 China The Department of Electrical and Computer Engineering University of Alberta EdmontonAB Canada College of Computer and Information Science Southwest University Chongqing400715 China

The granular-ball (GB)-based classifier introduced by Xia, exhibits adaptability in creating coarse-grained information granules for input, thereby enhancing its generality and flexibility. Nevertheless, the current GB-based classifiers rigidly assign a specific class label to each data instance and lacks of the necessary strategies to address uncertain instances. These far-fetched certain classification approachs toward uncertain instances may suffer considerable risks. To solve this problem, we construct a robust three-way classifier with shadowed GBs for uncertain data. Firstly, combine with information entropy, we propose an enhanced GB generation method with the principle of justifiable granularity. Subsequently, based on minimum uncertainty, a shadowed mapping is utilized to partition a GB into Core region, Important region and Unessential region. Based on the constructed shadowed GBs, we establish a three-way classifier to categorize data instances into certain classes and uncertain case. Finally, extensive comparative experiments are conducted with 2 three-way classifiers, 3 state-of-the-art GB-based classifiers, and 3 classical machine learning classifiers on 12 public benchmark datasets. The results show that our model demonstrates robustness in managing uncertain data and effectively mitigates classification risks. Furthermore, our model almost outperforms the other comparison methods in both effectiveness and efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

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：