检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interaction Prediction Based on Drug Subgraph Fingerprint Extraction Strategy and Subgraph Attention Mechanism 9th

Drug-Target Interaction Prediction Based on Drug Subgraph Fi...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Wang, Lizhi Zhang, Xiaolong Lin, Xiaoli Hu, Jing College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Realtime Industrial System Hubei Wuhan China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9783031466700

Drug discovery is a major focus of modern research, and predicting drug-target interactions is one of the strategies to facilitate this research process. Traditional laboratory methods have long time cycles and are relatively costly, so the use of high-precision virtual screening is essential. Previous virtual screens have only considered the sequence structure of the drug or the graph structure of the drug, without considering the role of the drug subgraph structure. Therefore, this paper adopts a method for extracting drug subgraphs and designs a strategy for extracting drug subgraph fingerprints. Then, the fingerprint vector data of the drugs are trained by the graph neural network to produce drug information vectors containing the spatial structure of the drug subgraph. Finally, the subgraph attention mechanism is used to update the information on protein targets, facilitating the model to extract more information about the target site. The experimental results show that the model can predict drug-target interactions well, outperforming the state-of-the-art model in all metrics. And it is also effective in both classification prediction and affinity regression prediction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Community discovery method based on complex network of data fusion based on the super network perspective

引用

International Journal of Computers and Applications 2021年第4期43卷 383-390页

作者： Pei, Li School of Computer Science & Technology Xi‘an University of Posts and Telecommunications Xi‘an China Shaanxi Key Laboratory of Network Data Intelligent Processing Xi‘an University of Posts and Telecommunications Xi‘an China Ministry of Education Key Lab For Intelligent Networks and Network Security Xi‘an Jiaotong University Xi‘an China

To enhance the computational efficiency and precision of community discovery, a community discovery algorithm with the mixed label based on the minimum description length (MDI) of information compression is proposed in this paper. Firstly, the community detection is converted to the information compression problem of seeking for an effective network structure and the quality evaluation function is constructed based on the MDL criterion. Secondly, the community discovery algorithm with heuristic mixed label movement is constructed based on the label node movement algorithm and Louvain community addition algorithm so as to reduce the quality evaluation function. Finally, the simulation experiment in the standard test set and API capture Sina microblog dataset shows that the proposed algorithm is superior to the selected comparison algorithm in computational efficiency and precision. © 2018 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

arXiv

引用

arXiv 2025年

作者： Yuan, Zenghui Shi, Jiawen Zhou, Pan Gong, Neil Zhenqiang Sun, Lichao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Duke University United States Lehigh University United States

Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse multimodal applications, such as autonomous driving and medical diagnosis, via plug-and-play without fine-tuning. This deployment paradigm increases the vulnerability of MLLMs to backdoor attacks. However, existing backdoor attacks against MLLMs achieve limited effectiveness and stealthiness. In this work, we propose BadToken, the first token-level backdoor attack to MLLMs. BadToken introduces two novel backdoor behaviors: Token-substitution and Token-addition, which enable flexible and stealthy attacks by making token-level modifications to the original output for backdoored inputs. We formulate a general optimization problem that considers the two backdoor behaviors to maximize the attack effectiveness. We evaluate BadToken on two open-source MLLMs and various tasks. Our results show that our attack maintains the model’s utility while achieving high attack success rates and stealthiness. We also show the real-world threats of BadToken in two scenarios, i.e., autonomous driving and medical diagnosis. Furthermore, we consider defenses including fine-tuning and input purification. Our results highlight the threat of our attack. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM App Store Analysis: A Vision and Roadmap

arXiv

引用

arXiv 2024年

作者： Zhao, Yanjie Hou, Xinyi Wang, Shenao Wang, Haoyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Huazhong University of Science and Technology Wuhan China

The rapid growth and popularity of large language model (LLM) app stores have created new opportunities and challenges for researchers, developers, users, and app store managers. As the LLM app ecosystem continues to evolve, it is crucial to understand the current landscape and identify potential areas for future research and development. This paper presents a forward-looking analysis of LLM app stores, focusing on key aspects such as data mining, security risk identification, development assistance, and market dynamics. Our comprehensive examination extends to the intricate relationships between various stakeholders and the technological advancements driving the ecosystem's growth. We explore the ethical considerations and potential societal impacts of widespread LLM app adoption, highlighting the need for responsible innovation and governance frameworks. By examining these aspects, we aim to provide a vision for future research directions and highlight the importance of collaboration among stakeholders to address the challenges and opportunities within the LLM app ecosystem. The insights and recommendations provided in this paper serve as a foundation for driving innovation, ensuring responsible development, and creating a thriving, user-centric LLM app landscape. Copyright © 2024, The Authors. All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Secure RFID-Assisted Authentication Protocol for Vehicular Cloud Computing Environment

引用

IEEE Transactions on intelligent Transportation systems 2024年第9期25卷 12528-12537页

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Tariq, Tayyaba Alenazi, Mohammed J. F. Das, Ashok Kumar University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Institute for Cyber Security School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Sichuan University Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518000 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Yunlin Douliu64002 Taiwan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500032 India

Vehicular network technology has made substantial advancements in recent years in the field of intelligent Transportation systems. Vehicular Cloud Computing (VCC) has emerged as a novel paradigm with a substantial increase in data exchange within Vehicular ad-hoc networks (VANETs). VCC integrates cloud computing, vehicular networking, and Internet of Things (IoT) technologies. It enables Infrastructure-to-Vehicle (I2V), Vehicle-to-Vehicle (V2V), and Vehicle-to-Device (V2D) communication. VCC optimizes vehicle, cloud infrastructure, and IoT resources while addressing significant communication security and vehicle-user privacy challenges. To address these issues, we developed an RFID-based authentication protocol for VCC based on a Henon map using a hash function. In addition, we also incorporated a Physical Unclonable Function (PUF) to resist physical tampering attacks. We validate the protocol's security formally and informally. The formal security analysis is conducted through a widely used RoR model. We use the Scyther simulation tool to verify the proposed protocol's security against various attacks. Moreover, we compare the performance of our protocol with similar existing protocols across important performance parameters such as communication and computation overheads and security attributes. The proposed protocol yields substantial improvements, demonstrating a 40.74% reduction in computation overhead and a 13.03% decrease in communication overhead as compared to related protocols, delivering both enhanced performance and resource efficiency. The analysis demonstrates its capacity to support secure communication in the VCC environment and satisfy desirable security attributes. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

GBSVM: Granular-ball Support Vector Machine

arXiv

引用

arXiv 2022年

作者： Xia, Shuyin Lian, Xiaoyu Wang, Guoyin Gao, Xinbo Chen, Jiancu Peng, Xiaoli The Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

GBSVM (Granular-ball Support Vector Machine) is a significant attempt to construct a classifier using the coarse-to-fine granularity of a granular-ball as input, rather than a single data point. It is the first classifier whose input contains no points. However, the existing model has some errors, and its dual model has not been derived. As a result, the current algorithm cannot be implemented or applied. To address these problems, this paper has fixed the errors of the original model of the existing GBSVM, and derived its dual model. Furthermore, a particle swarm optimization algorithm is designed to solve the dual model. The sequential minimal optimization algorithm is also carefully designed to solve the dual model. The solution is faster and more stable than the particle swarm optimization based version. The experimental results on the UCI benchmark datasets demonstrate that GBSVM has good robustness and efficiency. All codes have been released in the open source library at http://***/*** or https://***/syxiaa/GBSVM. Copyright © 2022, The Authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

Implementation and Performance Evaluation of Secure Addressing Method Based on 6LoWPAN Neighbor Discovery

SSRN

引用

SSRN 2024年

作者： Liu, Chao Chen, Fulong Industrial Intelligent Data Security Key Laboratory of Anhui Province Anhui Normal University Wuhu241002 China School of Computer and Information Anhui Normal University Wuhu241002 China

The successful implementation of IPv6 in low-power Internet of Things (IoT) nodes is crucial for the advancement of IoT. One of the primary challenges that IPv6 must address in the communication adaptation process of IoT nodes is the issue of secure lightweight addressing. Due to the open deployment and limited resources of these nodes, the current addressing method based on 6LoWPAN neighbor discovery (6LoWPAN-ND) is vulnerable to risks such as fabrication, spoofing, and replay attacks. In this paper, we discuss our design for security addressing strategies and implementation methods based on 6LoWPAN-ND, as well as provide a lightweight implementation on the widely used Contiki OS. The security strategies of MAC authentication, registration parameters authentication and NONCE verification ensure the legitimacy of registration messages, and DAD verification ensures the availability of addresses. MAC transmission based on the Address Registration Option (ARO) and hash authentication based on the Ascon-Hash mode guarantee a lightweight implementation. We evaluate and analyze the performance of the 6LoWPAN-ND secure addressing implementation, and compare it with the 6LoWPAN-ND addressing implementation without security strategy. Our findings indicate that the implementation of secure addressing results in an average increase in addressing latency of less than 1 second. Additionally, we observe a decrease of approximately 7.5% in the number of addressing ND messages, while the addressing traffic increased by approximately 11.7%. Furthermore, the average addressing energy consumption increased by approximately 2.6 mJ. These results demonstrate that the implemented security addressing method effectively meets the requirements of secure addressing with minimal increase in security overhead, making it suitable for low-power network nodes. © 2024, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Application Research of Vertical Federated Learning Technology in Banking Risk Control Model Strategy 21

Application Research of Vertical Federated Learning Technolo...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Luo, Yong Lu, Zhi Yin, Xiaofei Lu, Songfeng Weng, Yiting Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan China China Minsheng Banking Corp. Ltd. Beijing China Shenzhen Huazhong University of Science and Technology Research Institute Wuhan China Shu Lun Pan Beijing China

ISBN: (纸本)9798350329223

This study centers on the application of vertical federated learning technology in the context of Internet banking loans, with a particular focus on innovations in data privacy protection, risk control model algorithms, and secure multi-party computation. Currently, banking risk control strategies mainly rely on traditional data processing technologies, which often fall short in protecting user privacy and ensuring data usage efficiency. We adopt vertical federated learning technology, offering an innovative solution for the Internet banking loan scenario. Firstly, regarding data privacy protection, we propose a differential privacy mechanism to safeguard user-sensitive data. Secondly, we innovatively apply risk control model algorithms, facilitating collaborative modeling across multiple Internet loan platforms through federated learning. Furthermore, we introduce secure multi-party computation technology to ensure the secure transmission of data and confidentiality of computation processes during federated learning. Through empirical experiments on real Internet loan datasets, we validate the effectiveness and feasibility of our proposed methods. After implementing our risk control model, the credit approval rate increased from 3.44% to 18.2%, with a single-day high reaching 25.53%. The average loan amount increased by 7,700 yuan, and the average interest rate slightly declined by 0.48%, marking a significant improvement and breakthrough compared to traditional risk control models. This study offers innovative solutions for data privacy protection and risk control in the Internet loan scenario, providing safer and more reliable services for financial institutions and users. Moreover, our methods possess high practicality and promotional value. The potential widespread impact on the industry is profound. © 2023 IEEE.

关键词： Risk management

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：