检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qian, Xinyuan Gao, Jiaran Zhang, Yaodan Zhang, Qiquan Liu, Hexin Garcia, Leibny Paola Li, Haizhou The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Electrical Engineering and Telecommunications The University of New South Wales Sydney2052 Australia The College of Computing and Data Science Nanyang Technological University Singapore The Center for Language and Speech Processing Johns Hopkins University United States The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen51872 China

Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas contextual visual cues from the surrounding environment have been overlooked: for example, when we see a dog bark, our brain has the innate ability to discern and filter out the barking noise. To this end, in this paper, we introduce a novel task, i.e. Scene-aware AudioVisual Speech Enhancement (SAV-SE). To our best knowledge, this is the first proposal to use rich contextual information from synchronized video as auxiliary cues to indicate the type of noise, which eventually improves the speech enhancement performance. Specifically, we propose the VC-S2E method, which incorporates the Conformer and Mamba modules for their complementary strengths. Extensive experiments are conducted on public MUSIC, AVSpeech and AudioSet datasets, where the results demonstrate the superiority of VC-S2E over other competitive methods. We will make the source code publicly available. Project demo page: https://***/ © 2024, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao School of Cyber Science and Engineering Huazhong University of Science and Technology China 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 Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China School of Information and Communication Technology Griffith University Australia University of Technology Sydney Australia RMIT University Australia

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: SPONGE for triggering widespread misidentifications and BLINDING for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (∼10%-60% absolute and ∼2-7× relative) in attack efficacy over state-of-the-art attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Multi-modal Multi-objective Algorithm Based on Dynamic Niche Updating 11th

Two-Stage Multi-modal Multi-objective Algorithm Based on Dy...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Ji, Haonian Chen, Hongmei Mi, Yong Institute of Artificial Intelligence School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Southwest Jiaotong University Chengdu 611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 China

ISBN: (纸本)9783031927409

In solving multi-modal multi-objective optimization problems (MMOPs), objective and decision space changes need to be considered. However, many multi-modal multi-objective evolutionary algorithms (MMOEAs) tend to prioritize diversity in the objective space during the optimization process, often leading to suboptimal diversity and distribution in the decision space. This study proposes the Dynamic-Niche-Based Two-Stage Evolution (DNTE) approach to address this issue. DNTE employs differential evolutionary strategies in two stages, utilizing dynamic niche to enhance solution viability and optimize decision space distribution at different phases. In the first stage, the dynamic niche is used to restrict the dominance range of Pareto domination. In contrast, in the second stage, it is integrated with differential evolution to refine the distribution of the decision space. Combining DNTE with DN-NSGA-II enhances the capability of solving MMOPs and demonstrates superior performance compared to other evolutionary algorithms on MMF and MMMOP benchmark functions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Differential evolution Dynamic niche Multi-modal multi-objective optimization problem

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired Portfolio Optimization In The QUBO Framework

arXiv

引用

arXiv 2024年

作者： Lu, Ying-Chang Fu, Chao-Ming Yu, Lien-Po Chang, Yen-Jui Chang, Ching-Ray Department of Physics National Taiwan University Taipei Taiwan Institute for Information Industry Taipei Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City Taiwan Quantum Information Center Chung Yuan Christian University Taoyuan City Taiwan

A quantum-inspired optimization approach is proposed to study the portfolio optimization aimed at selecting an optimal mix of assets based on the risk-return trade-off to achieve the desired goal in investment. By integrating conventional approaches with quantum-inspired methods for penalty coefficient estimation, this approach enables faster and accurate solutions to portfolio optimization which is validated through experiments using a real-world dataset of quarterly financial data spanning over ten-year period. In addition, the proposed preprocessing method of two-stage search further enhances the effectiveness of our approach, showing the ability to improve computational efficiency while maintaining solution accuracy through appropriate setting of parameters. This research contributes to the growing body of literature on quantum-inspired techniques in finance, demonstrating its potential as a useful tool for asset allocation and portfolio management. Copyright © 2024, The Authors. All rights reserved.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

引用

International Conference on Software Engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-view Clustering Based on Joint Concept Decomposition and Anchor Graph Learning 11th

Incomplete Multi-view Clustering Based on Joint Concept Dec...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Li, Zhuowen Chen, Hongmei Xiang, Biao Yuan, Zhong Luo, Chuan Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu 611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 China College of Computer Science Sichuan University Chengdu 610065 China

ISBN: (纸本)9783031927430

The main objective of incomplete multi-view clustering is to effectively utilize the existing view information to fill in the missing data and to mine the complementary information and potential associations between multiple views to effectively group samples. The existing primary means for recovering missing information are classified into two parts: one uses matrix decomposition or low-rank constraints to fill in the missing views, and the other constructs multiple graph structures and uses graph regularization to recover the corresponding missing parts. However, the two methods are relatively independent and are not used jointly to improve the model performance. This paper proposes an incomplete multi-view clustering method with complete clustering metrics and complete anchor graphs (CFAG). Specifically, each view’s missing samples are recovered by a matrix of consistent clustering metrics and represented by an anchor graph. The recovered complete data performs anchor graph construction and anchor learning and utilizes the orthogonal variation principle to learn the consistency structure of multiple anchor graphs to mine the complementary information among multiple views. The clustering metrics are obtained based on the consistency structure, and the consistency of the clustering metrics is also considered to obtain the final clustering results. The effectiveness of the proposed method is verified on multiple datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anchor graph Incomplete multi-view clustering Missing views recovery

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection Multi-copy Provable data Possession Supporting data Reliability 5th

Privacy Protection Multi-copy Provable Data Possession Suppo...

引用

5th International Conference on Blockchain and Trustworthy Systems, BlockSys 2023

作者： Zhang, Feng Wen, Bin Yan, Yifei Zeng, Zhaowu Zhou, Wei School of Information Science and Technology Hainan Normal University Haikou571158 China Cloud Computing and Big Data Research Center Hainan Normal University Haikou571158 China Key Laboratory of Data Science and Smart Education Ministry of Education Hainan Normal University Haikou571158 China

ISBN: (纸本)9789819981007

With the development of technology, a massive amount of data continues to emerge, and there is still a strong demand for data storage. Outsourcing data to cloud service providers has become a common practice. Although cloud storage offers the advantage of location-independent data access and reduces burdens such as hardware and software maintenance, this service still faces some challenges in terms of privacy and data reliability. To address this issue, we present Privacy-preserving Multi-copy Provable data Possession supporting data Reliability (PMPDP-R). Our proposal ensures the integrity, reliability, and freshness of data by designing Timestamp-based Double-layer Merkle Hash Tree (TD-MHT), a novel dynamic structure for multicopy storage. Furthermore, our approach uses random masking techniques to develop unique replica blocks and safeguard privacy. We’ve also ensured data reliability by enabling PMPDP-R to locate damaged data blocks to aid recovery. The experimental analysis proves that our scheme is both practical and effective. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, 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

A Self-Supervised Transfer Learning Framework for Gland Segmentation in Colorectal Cancer Histopathology with Limited Labeled data 2nd

A Self-Supervised Transfer Learning Framework for Gland Segm...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Wen, Huer Wu, Yan Huang, De-Shuang Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology Shanghai East Hospital School of Medicine Tongji University Shanghai200123 China Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China Ningbo Institute of Digital TwinEastern Institute of Technology No. 568 Tongxin Road Zhuangshi Street Zhejiang Ningbo315201 China

ISBN: (纸本)9789819619061

Accurate gland segmentation in colorectal cancer histopathology images is crucial for diagnosis and grading but is hampered by the limited availability of annotated data. To develop a robust and accurate gland segmentation method that effectively leverages unlabeled data to overcome the limitations of small annotated datasets. We propose a novel framework that combines self-supervised learning and transfer learning. A vision transformer is pre-trained using DINOv2 on a large unlabeled dataset (IMP-CRS-2024) and then fine-tuned on the GlaS dataset using a lightweight decoder and a boundary-aware loss function that combines Dice loss and a distance transform-weighted boundary loss. Our method achieves state-of-the-art performance on the GlaS dataset, surpassing existing methods in terms of F1-score, Object Dice, and Object Hausdorff distance. An ablation study confirms the benefits of both the self-supervised pre-training and the boundary-aware loss. Our approach effectively addresses the challenge of limited annotated data in gland segmentation, offering a promising solution for improving the accuracy and efficiency of colorectal cancer diagnosis. The framework can be generalized to other histopathology image analysis tasks and cancer types. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning

Challenges and Approaches for Mitigating Byzantine Attacks i...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Junyu Shi Wei Wan Shengshan Hu Jianrong Lu Leo Yu Zhang School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Information Technology Deakin University

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, Byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against Byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new Byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating Byzantine attacks in FL.

关键词： Wireless communication Training Privacy data privacy Federated learning Distance learning Taxonomy

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：