检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Amsterdam Netherlands

Neural ranking models (NRMs) have shown remarkable success in recent years, especially with pre-trained language models. However, deep neural models are notorious for their vulnerability to adversarial examples. Adversarial attacks may become a new type of web spamming technique given our increased reliance on neural information retrieval models. Therefore, it is important to study potential adversarial attacks to identify vulnerabilities of NRMs before they are deployed. In this paper, we introduce the Word Substitution Ranking Attack (WSRA) task against NRMs, which aims to promote a target document in rankings by adding adversarial perturbations to its text. We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list. This attack setting is realistic in real-world search engines. We propose a novel Pseudo Relevance-based ADversarial ranking Attack method (PRADA) that learns a surrogate model based on Pseudo Relevance Feedback (PRF) to generate gradients for finding the adversarial perturbations. Experiments on two web search benchmark datasets show that PRADA can outperform existing attack strategies and successfully fool the NRM with small indiscernible perturbations of text. Copyright © 2022, The Authors. All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Remote Visitor System Based on NFC technology 10th

Design and Implementation of Remote Visitor System Based on ...

引用

10th International Conference on Computer Engineering and networks, CENet 2020

作者： Wang, Zhiqiang Gao, Shichun Xue, Meng Ju, Xinyu Wang, Xinhao Lv, Xin Li, Yang Yang, Tao State Information Center Beijing100045 China Beijing Electronic Science and Technology Institute Beijing100070 China Key Lab of Information Network Security Ministry of Public Security Shanghai200000 China

ISBN: (纸本)9789811584619

Most visitor systems information management is at a low level, and the processing method is still semi-manual registration. To improve the level of automation of the visitor system, this paper designs a remote visitor system based on NFC technology deployed on the Android smart-phone platform. It reads and emulates card data through NFC technology and adopts SM series algorithm to encrypt and decrypt the transmitted data. The system effectively solves the problems about security and automation in the traditional guest system. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Identification System Based on Fingerprint and Finger Vein 10th

Identification System Based on Fingerprint and Finger Vein

引用

10th International Conference on Computer Engineering and networks, CENet 2020

作者： Wang, Zhiqiang Hou, Zeyang Wang, Zhiwei Li, Xinyu Wei, Bingyan Lv, Xin Yang, Tao State Information Center Beijing100045 China Beijing Electronic Science and Technology Institute Beijing100070 China Key Lab of Information Network Security Ministry of Public Security Shanghai200000 China

ISBN: (纸本)9789811584619

In recent years, with the rapid development of information technology, more and more attention has been paid to information security. Biometrics is an important way to ensure information security, and digital vein recognition is an important branch of biometrics, which has an irreplaceable position in the field of information security. However, the traditional finger vein recognition is vulnerable to attacks such as replay, template tampering, and forging original features, which leads to the destruction of the authentication system. This paper proposes a solution to encrypt the feature points of finger vein with the key generated by the relative difference of fingerprint detail points based on the SM4 algorithm to realize the double encryption authentication of user information, so as to improve the security and accuracy of user identity identification and meet the increasing requirements of high security. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Discriminative Semantic Ranker for Question Retrieval 21

A Discriminative Semantic Ranker for Question Retrieval

引用

11th ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR 2021

作者： Cai, Yinqiong Fan, Yixing Guo, Jiafeng Zhang, Ruqing Lan, Yanyan Cheng, Xueqi University of Chinese Academy of Sciences Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute for Ai Industry Research Tsinghua University Beijing China

ISBN: (纸本)9781450386111

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage ranker aims to recall potentially relevant questions from a large repository, and the latter stages attempt to re-rank the retrieved results. Most existing works on question retrieval mainly focused on the re-ranking stages, leaving the first-stage ranker to some traditional term-based methods. However, term-based methods often suffer from the vocabulary mismatch problem, especially on short texts, which may block the re-rankers from relevant questions at the very beginning. An alternative is to employ embedding-based methods for the first-stage ranker, which compress texts into dense vectors to enhance the semantic matching. However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance. In this work, we aim to tackle the dilemma of the first-stage ranker, and propose a discriminative semantic ranker, namely DenseTrans, for high-recall retrieval. Specifically, DenseTrans is a densely connected Transformer, which learns semantic embeddings for texts based on Transformer layers. Meanwhile, DenseTrans promotes low-level features through dense connections to keep the discriminative power of the learned representations. DenseTrans is inspired by DenseNet in computer vision (CV), but poses a new way to use the dense connectivity which is totally different from its original design purpose. Experimental results over two question retrieval benchmark datasets show that our model can obtain significant gain on recall against strong term-based methods as well as state-of-the-art embedding-based methods. © 2021 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models

arXiv

引用

arXiv 2022年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng Chen, Wei Fan, Yixing de Rijke, Maarten Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

Neural ranking models (NRMs) have achieved promising results in information retrieval. NRMs have also been shown to be vulnerable to adversarial examples. A typical Word Substitution Ranking Attack (WSRA) against NRMs was proposed recently, in which an attacker promotes a target document in rankings by adding human-imperceptible perturbations to its text. This raises concerns when deploying NRMs in real-world applications. Therefore, it is important to develop techniques that defend against such attacks for NRMs. In empirical defenses adversarial examples are found during training and used to augment the training set. However, such methods offer no theoretical guarantee on the models’ robustness and may eventually be broken by other sophisticated WSRAs. To escape this arms race, rigorous and provable certified defense methods for NRMs are needed. To this end, we first define the Certified Top-K Robustness for ranking models since users mainly care about the top ranked results in real-world scenarios. A ranking model is said to be Certified TopK Robust on a ranked list when it is guaranteed to keep documents that are out of the top K away from the top K under any attack. Then, we introduce a Certified Defense method, named CertDR, to achieve certified top-K robustness against WSRA, based on the idea of randomized smoothing. Specifically, we first construct a smoothed ranker by applying random word substitutions on the documents, and then leverage the ranking property jointly with the statistical property of the ensemble to provably certify top-K robustness. Extensive experiments on two representative web search datasets demonstrate that CertDR can significantly outperform state-of-the-art empirical defense methods for ranking models. © 2022, CC0.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Mining unseen classes via regional objectness: a simple baseline for incremental segmentation 22

Mining unseen classes via regional objectness: a simple base...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Zekang Zhang Guangyu Gao Zhiyuan Fang Jianbo Jiao Yunchao Wei School of Computer Science Beijing Institute of Technology School of Computer Science University of Birmingham WEI Lab Institute of Information Science Beijing Jiaotong University and Beijing Key Laboratory of Advanced Information Science and Network

ISBN: (纸本)9781713871088

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental semantic segmentation, such a phenomenon often becomes much worse due to the background shift, i.e., some concepts learned at previous stages are assigned to the background class at the current training stage, therefore, significantly reducing the performance of these old concepts. To address this issue, we propose a simple yet effective method in this paper, named Mining unseen Classes via Regional Objectness for Segmentation (MicroSeg). Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages. Therefore, to avoid forgetting old knowledge at the current training stage, our MicroSeg first splits the given image into hundreds of segment proposals with a proposal generator. Those segment proposals with strong objectness from the background are then clustered and assigned newly-defined labels during the optimization. In this way, the distribution characterizes of old concepts in the feature space could be better perceived, relieving the catastrophic forgetting caused by the background shift accordingly. Extensive experiments on Pascal VOC and ADE20K datasets show competitive results with state-of-the-art, well validating the effectiveness of the proposed MicroSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Collaborative Metric Learning with Mixed-Scale Groups for General Object Retrieval

arXiv

引用

arXiv 2024年

作者： Kan, Shichao Deng, Yuhai Liang, Yixiong Cen, Lihui Qu, Zhe Cen, Yigang He, Zhihai School of Computer Science and Engineering Central South University Hunan Changsha410083 China School of Automation Central South University Hunan Changsha410083 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China Pengcheng Lab Shenzhen518066 China

The task of searching for visual objects in a large image dataset is difficult because it requires efficient matching and accurate localization of objects that can vary in size. Although the segment anything model (SAM) offers a potential solution for extracting object spatial context, learning embeddings for local objects remains a challenging problem. This paper presents a novel unsupervised deep metric learning approach, termed unsupervised collaborative metric learning with mixed-scale groups (MS-UGCML), devised to learn embeddings for objects of varying scales. Following this, a benchmark of challenges is assembled by utilizing COCO 2017 and VOC 2007 datasets to facilitate the training and evaluation of general object retrieval models. Finally, we conduct comprehensive ablation studies and discuss the complexities faced within the domain of general object retrieval. Our object retrieval evaluations span a range of datasets, including BelgaLogos, Visual Genome, LVIS, in addition to a challenging evaluation set that we have individually assembled for open-vocabulary evaluation. These comprehensive evaluations effectively highlight the robustness of our unsupervised MS-UGCML approach, with an object level and image level mAPs improvement of up to 6.69% and 10.03%, respectively. The code is publicly available at https://***/dengyuhai/MSUGCML. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

RDG-TE: Link reliability-aware DRL-GNN-based traffic engineering in SDN

引用

Expert Systems with Applications 2025年 265卷

作者： Farhan, Muhammad Shah, Nadir Wang, Lei Muntean, Gabriel-Miro Song, Houbing Herbert School of Software Dalian University of Technology Dalian China Department of Computer Science COMSATS University Islamabad Wah Campus Pakistan Key Lab of Ubiquitous Network and Service Software of Liaoning Province China School of Electronic Engineering Dublin City University Dublin Ireland Department of Information Systems University of Maryland Baltimore United States

The existing advanced machine learning approaches based on Graph Neural networks (GNN) for efficient traffic engineering (TE) in Software Defined networking (SDN) overlook consideration of link reliability values. Link reliability is a very important parameter, directly linked to end-to-end delay for data packet transmission, and can be used to improve the delivery performance. This research article proposes two versions of RDG-TE, a novel model that integrates Deep Reinforcement Learning (DRL) and GNN in order to solve efficiently network TE problems by considering link reliability in both model training and reward computation. The proposed model enables improved performance by more accurately predicting the SDN network behavior in case of link failure. Testing results show that, in comparison to the closest state-of-art approach, our proposed approach reduces the number of disturbed flows by 24.19% and the hop count by 35.38% while also increases the reliable route prediction accuracy by 40.17%. © 2024 Elsevier Ltd

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Di-defects synergy boost electrocatalysis hydrogen evolution over two-dimensional heterojunctions

引用

Nano Research 2022年第1期15卷 677-684页

作者： Yan Cui Xiaoyu Guo Jian Zhang Xing’ao Li Xinbao Zhu Wei Huang Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Ministry of EducationNanjing University of Posts and TelecommunicationsNanjing 210003China New Energy Technology Engineering Lab of Jiangsu Province School of ScienceNanjing University of Posts&Telecommunications(NUPT)Nanjing 210023China Key Laboratory for Organic Electronics and Information Displays&Institute of Advanced Materials(LAM) Jiangsu National Synergetic Innovation Center for Advanced Materials(SICAM)Nanjing University of Posts&Telecommunications(NUPT)Nanjing 210023China College of Chemical Engineering Nanjing Forestry UniversityNanjing 210037China Shaanxi Institute of Flexible Electronics(SIFE) Northwestern Polytechnical University(NPU)}127 West Youyi RoadXian 710072China

Electronic modulation on the inert basal plane of transition-metal dichalcogenides(TMDs)through vacancy defect excitation,although extremely challenging,is urgent for understanding the factors that impact the hydrogen evolution reaction(HER)catalytic ***,ultrathin WS2 nanosheets with precise quantitative single atomic S-vacancy on the inert basal plane were flexible prepared through hydrogen peroxide etching *** as-synthesized single atomic S-vacancy defect WS2(SVD-WS2)nanoflake with the activated basal plane exhibited an impressive overpotential of 137 mV at a current density of 10 mA·cm^(-2) and a Tafel slope of 53.9 mV dec^(-1).Furthermore,anchoring on the defect graphene matrix,the assembled two-dimensional(2D)stacking heterojunction exhibits further enhanced HER catalytic activity(an overpotential of 108 mV vs.10 mA·cm^(-2) and a Tafel slope of 48.3 mV·dec^(-1))and stability(〜10%decline after 9,000 cycles),which attributed to the electronic structure modulation from the synergetic interactions between SVD-WS_(2) and defect *** finding provides a smart defects introduce strategy to trigger high-efficiency hydrogen evolution over WS_(2) nanosheets and a general 2D heterojunctions fabricated inspiration based on strong interaction interface.

关键词： S-vacancies defect graphene hydrogen evolution reaction heterojunctions

来源：评论

学校读者我要写书评

暂无评论

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector

arXiv

引用

arXiv 2024年

作者： Li, Kaiyu Cao, Xiangyong Deng, Yupeng Song, Jiayi Liu, Junmin Meng, Deyu Wang, Zhi School of Software Engineering Xi’an Jiaotong University Xi’an710049 China School of Computer Science and Technology Ministry of Education Key Lab For Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an China Guangdong Guangzhou China

Change Detection (CD) aims to identify pixels with semantic changes between images. However, annotating massive numbers of pixel-level images is labor-intensive and costly, especially for multi-temporal images, which require pixel-wise comparisons by human experts. Considering the excellent performance of visual language models (VLMs) for zero-shot, open-vocabulary, etc. with prompt-based reasoning, it is promising to utilize VLMs to make better CD under limited labeled data. In this paper, we propose a VLM guidance-based semisupervised CD method, namely SemiCD-VL. The insight of SemiCD-VL is to synthesize free change labels using VLMs to provide additional supervision signals for unlabeled data. However, almost all current VLMs are designed for single-temporal images and cannot be directly applied to bi- or multi-temporal images. Motivated by this, we first propose a VLM-based mixed change event generation (CEG) strategy to yield pseudo labels for unlabeled CD data. Since the additional supervised signals provided by these VLM-driven pseudo labels may conflict with the original pseudo labels from the consistency regularization paradigm (e.g. FixMatch), we propose the dual projection head for de-entangling different signal sources. Further, we explicitly decouple the bi-temporal images semantic representation through two auxiliary segmentation decoders, which are also guided by VLM. Finally, to make the model more adequately capture change representations, we introduce contrastive consistency regularization by constructing feature-level contrastive loss in auxiliary branches. Extensive experiments show the advantage of SemiCD-VL. For instance, SemiCD-VL improves the FixMatch baseline by +5.3 IoUc on WHU-CD and by +2.4 IoUc on LEVIR-CD with 5% labels, and SemiCD-VL requires only 5% to 10% of the labels to achieve performance similar to the supervised methods. In addition, our CEG strategy, in an un-supervised manner, can achieve performance far superior to state-of-t

关键词： Visual languages

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：