检索结果-内蒙古大学图书馆

International Workshop on Quality of Service

作者： Weipeng Cao Xi Tao Yinghui Pan Ye Liu Zhong Ming Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

The advantages of resource elasticity and proactive data backup in cloud databases have attracted a large number of users to consider deploying their IT systems in the cloud. Factors such as performance, reliability, security, and ease of use are the most important considerations for users when choosing to migrate to the cloud. This paper mainly discusses the necessity of Quality of Service (QoS) awareness for cloud applications in the current public cloud environment, as well as the technological trends and challenges associated with it.

关键词： Cloud computing Databases Quality of service Elasticity Market research Real-time systems Security

来源：评论

学校读者我要写书评

暂无评论

Multi-Turn Jailbreaking Large Language Models via Attention Shifting 39

Multi-Turn Jailbreaking Large Language Models via Attention ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Xiaohu Mo, Fan Wen, Ming Gu, Tu Zheng, Huadi Jin, Hai Shi, Jie China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab School of Computer Science and Technology HUST China JinYinHu Laboratory China Huawei International China

ISBN: (纸本)157735897X

Large Language Models (LLMs) have achieved significant performance in various natural language processing tasks but also pose safety and ethical threats, thus requiring red teaming and alignment processes to bolster their safety. To effectively exploit these aligned LLMs, recent studies have introduced jailbreak attacks based on multi-turn dialogues. These attacks aim to prompt LLMs to generate harmful or biased content by guiding them through contextual content. However, the underlying reasons for the effectiveness of multi-turn jailbreaks remain unclear. Existing attacks often focus on optimizing queries and escalating toxicity to construct dialogues, lacking a thorough analysis of the inherent vulnerabilities of LLMs. In this paper, we first conduct an in-depth analysis of the differences between single-turn and multi-turn jailbreaks and find that successful multi-turn jailbreaks can effectively disperse the attention of LLMs on keywords associated with harmful behaviors, especially in historical responses. Based on this, we propose ASJA, a new multi-turn jailbreak approach by shifting the attention of LLMs, specifically by iteratively fabricating the dialogue history through a genetic algorithm to induce LLMs to generate harmful content. Extensive experiments on three LLMs and two datasets show that our approach surpasses existing approaches in jailbreak effectiveness, the stealth of jailbreak prompts, and attack efficiency. Our work emphasizes the importance of enhancing the robustness of LLMs’ attention mechanism in multi-turn dialogue scenarios for a better defense strategy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MBAPIS: Multi-Level Behavior Analysis Guided Program Interval Selection for Microarchitecture Studies

MBAPIS: Multi-Level Behavior Analysis Guided Program Interva...

引用

International Conference on Parallel Architecture and Compilation Techniques (PACT)

作者： Hongwei Cui Yujie Cui Honglan Zhan Shuhao Liang Xianhua Liu Chun Yang Xu Cheng Engineering Reserach Center of Microprocessor & System Ministry of Education School of Computer Science Peking University Beijing National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing

Understanding program behavior is crucial in computer architecture research, but the growing size of benchmarks makes analyzing and simulating entire programs increasingly challenging. In practice, researchers often select representative program intervals for analysis and testing. These intervals are different sections of continuous execution of a program. SimPoint is a well-known method for selecting representative intervals using hardware-independent information. However, when focusing on a specific microarchitecture study, it is desirable to select intervals that are more relevant to that study. For instance, intervals with more branch mispredictions are more appropriate for branch prediction studies. We refer to these intervals as “tailored intervals” for branch prediction studies. This paper presents a Multi-level Behavior Analysis guided Program Interval Selection (MBAPIS) for selecting tailored intervals. For a given microarchitecture study, the first level of MBAPIS uses hardware performance counters to prioritize selecting the intervals that exhibit clearer microarchitectural characteristics relevant to that study. The second level analyzes the processor performance bottlenecks to further select the intervals where the concerned microarchitecture design more strongly impacts performance. Finally, MBAPIS performs clustering analysis with the basic block information of each interval selected by the first two levels, and selects the representative intervals among them while preserving the diverse software behavior. Additionally, we present a general and extensible interval-replaying design to accurately re-execute selected intervals. The SPEC CPU2006 and CPU2017 benchmarks are used for evaluation. The results demonstrate that MBAPIS can select representative and tailored intervals for two typical microarchi-tecture studies and deliver accurate estimates of the concerned hardware events for all tailored intervals in each benchmark, with an average error rate of

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Ocean Scene Video Captioning with Multimodal Pre-Training and Video-Swin-Transformer

Enhancing Ocean Scene Video Captioning with Multimodal Pre-T...

引用

Annual Conference of Industrial Electronics Society

作者： Xinyu Chen Meng Zhao Fan Shi Meng'en Zhang Yu He Shengyong Chen Laboratory of Computer Vision and System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin China Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing China

With the success of multimodal pre-training models in the video-language field and various downstream tasks, previous multimodal models used 3DCNN networks as video feature extractors, which have limitations in interacting and fusing with text features. This paper proposes a multimodal pre-training model that utilizes a Video-Swin-Transformer-based network to encode both video and text data, to achieve better performance in video understanding. The model consists of four modules: video encoder, text encoder, interact encoder, and caption decoder to accomplish the task of ocean scene video captioning. A dataset of ocean scene videos, including various content types such as sea surfaces and shores, is also constructed. The training process is divided into two stages: pre-training and fine-tuning. Pre-training is performed on the Howto100m dataset to allow the model to learn video captions in natural scenes and complete video-language matching tasks. The fine-tuning stage is then performed on the ocean1000 dataset to better understand the events and content in ocean scene videos and generate captions that conform to ocean scene video descriptions. The model achieves satisfying results on both the public dataset YouCook2 and the proprietary dataset Ocean1000, demonstrating its ability in video-text information fusion and interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A passive DDoS attack detection approach based on abnormal analysis in SDN environment 4

A passive DDoS attack detection approach based on abnormal a...

引用

2021 4th International Conference on computer Information science and Application Technology, CISAT 2021

作者： Sun, Shimin Zhang, Xinchao Huang, Wentian Xu, Aixin Wang, Xiaofan Han, Li Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Computer Science and Technology Tiangong University Tianjin300387 China National Engineering Laboratory for Computer Virus Prevention and Control Technology School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Most of the detection methods against DDoS attacks are based on periodic detection, which leads to high communication overhead, untimely detection, and slow attack response. This paper proposes a passive abnormality detection approach. First, we record the two flow-table characteristics of the regular switches. Then, based on dynamic threshold method and Grubbs outlier test method, we make a determination of abnormal switches. This method reduces the amount of data duplication and regular traffic collection. Moreover, we use Support Vector Machine (SVM) algorithm to evaluate the performance of the passive anomaly detection method. The experiment results show a better performance than active period DDoS attack detection approaches. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 Licence.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Time Slot Correlation-Based Caching Strategy for Information-Centric Satellite Networks 1

引用

11th EAI International Conference on MOBILe Wireless MiddleWARE, Operating systems and Applications, MOBILWARE 2022

作者： Xu, Rui Di, Xiaoqiang Chen, Jing Cao, Jinhui Luo, Hao Wang, Haowei Qi, Hui He, Xiongwen Lei, Wenping School of Computer Science and Technology Changchun University of Science and Technology Changchun130022 China School of Information Engineering Henan Institute of Science and Technology Xinxiang453003 China Jilin Province Key Laboratory of Network and Information Security Changchun University of Science and Technology Changchun130022 China Information Center Changchun University of Science and Technology 130022 Changchun China Beijing Institute of Spacecraft System Engineering Beijing100094 China Beijing Institute of Space Mechanic and Electricity Beijing100094 China

ISBN: (数字)9783031344978

ISBN: (纸本)9783031344961

With the successful manufacture of highly stable and high-performance satellite processors, caching on satellites has become possible. Information Centric Networking (ICN) is introduced to satellite networks to address the growing need for diverse data services. However, existing caching policies in ICN still suffer from the shortage of rational planning of cache locations and redundancy of cache contents. Consequently, the time slot correlation-based caching strategy for satellite networks (TSCCS) is proposed. Firstly, the index of time slot correlation is designed to quantify the neighboring time slots’ coupling relationship, and then the DSAM network model with time slot correlation is established. Secondly, the significance of satellite nodes is evaluated from the local and global perspectives respectively based on the eigenvector centrality algorithm to filter out the dynamic set of cache nodes. Finally, probabilistic caching is performed at the set of caching nodes with the goal of reducing cached content redundancy, considering content popularity and access delay. The simulated outcomes indicate that the TSCCS caching policy is superior to the comparison method in the areas of cache hit rate, request latency, and server load. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing 39

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Great Bay University China

ISBN: (纸本)157735897X

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. Our codes will be made publicly available. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PB-UAP: Hybride Universal Adversarial Attack for Image Segmentation

PB-UAP: Hybride Universal Adversarial Attack for Image Segme...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yufei Song Ziqi Zhou Minghui Li Xianlong Wang Hangtao Zhang Menghao Deng Wei Wan Shengshan Hu Leo Yu Zhang 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 School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, i.e., adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model’s predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.

关键词： Training Image segmentation Perturbation methods Semantics Scattering Signal processing Predictive models Network architecture Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Algorithm for Energy and Performance Optimization of Computational Offloading in Mobile Edge Computing

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Khan, Israr Raza, Salman Rehman, Waheed Ur Khan, Razaullah Nahida, Kiran Tao, Xiaofeng National Engineering Laboratory for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science National Textile University Faisalabad Pakistan Department of Computer Science University of Peshawar Peshawar Pakistan Department of Computer Science University of Engineering and Technology Mardan Pakistan Beijing Laboratory of Advanced Information Network Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications China

Mobile edge computing (MEC) has produced incredible outcomes in the context of computationally intensive mobile applications by offloading computation to a neighboring server to limit the energy usage of user equipment (UE). However, choosing a pool of application components to offload in addition to the volume of data transfer along with the latency in communication is an intricate issue. In this article, we introduce a novel energy-efficient offloading scheme based on deep neural networks. The proposed scheme trains an intelligent decision-making model that picks a robust pool of application components. The selection is based on factors such as the remaining UE battery power, network conditions, the volume of data transfer, required energy by the application components, postponements in communication, and computational load. We have designed the cost function taking all the mentioned factors, get the cost for all conceivable combinations of component offloading decisions, pick the robust decisions over an extensive dataset, and train a deep neural network as a substitute for the exhaustive computations associated. Model outcomes illustrate that our proposed scheme is proficient in the context of accuracy, root mean square error (RMSE), mean absolute error (MAE), and energy usage of UE. © 2023 Israr Khan et al.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Adapting the Simulated Annealing Algorithm to Enhance the Performance of the LEACH Protocol

Adapting the Simulated Annealing Algorithm to Enhance the Pe...

引用

International Conference on computer and Applications (ICCA)

作者： Mohammed Benhadji Kaddi Mohammed Omari Mohammed Material Sciences Department Laboratory of Energy Environment and Information System (LEESI) University of Adrar Algeria Mathematics and Computer Science Department LDDI Laboratory University of Adrar Algeria Computer Science and Engineering Department American University of Ras Al Khaimah Ras Al Khaimah United Arab Emirates

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

In parallel with the proliferation and extension of wireless sensor networks (WSNs), as well as the diversity of their applications, such networks continue to fail to operate for lengthy periods of time due to node failure and the inability to replace sensor batteries in most circumstances. This hinders the networks' ability to remain operational over extended periods. That necessitates making the best and most efficient use of the nodes' energy. Hierarchical clustering methods augmented with metaphysical algorithms have produced amazing benefits in terms of network longevity. One of the most significant of these algorithms that draws inspiration from nature and yields excellent results is the simulated annealing technique. In this research, we report on our analysis of this method and how it performs best when used to optimize routing in WSN.

关键词： Wireless sensor networks Protocols Heuristic algorithms Metaheuristics Energy conservation Clustering algorithms Simulated annealing Spread spectrum communication Routing Testing

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：