检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong 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 Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation

引用

ACM Transactions on Recommender Systems 2024年第4期2卷 1-27页

作者： Xiangmeng Wang Qian Li Dianer Yu Qing Li Guandong Xu Data Science and Machine Intelligence Lab University of Technology Sydney Broadway Australia School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia Hong Kong Polytechnic University Hong Kong China

Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this article, we propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy), which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art m

关键词： Fairness-aware Recommendation Off-policy Learning Counterfactual Risk Minimization Heterogeneous Information Network

来源：评论

学校读者我要写书评

暂无评论

BADROBOT: JAILBREAKING EMBODIED LLMS IN THE PHYSICAL WORLD

arXiv

引用

arXiv 2024年

作者： Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu 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 Beihang University China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BADROBOT, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge’s flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BADROBOT’s attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BADROBOT. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

OUTLIER SYNTHESIS VIA HAMILTONIAN MONTE CARLO FOR OUT-OF-DISTRIBUTION DETECTION

arXiv

引用

arXiv 2025年

作者： Li, Hengzhuang Zhang, Teng National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS. Our code is available at: https://***/Fir-lat/HamOS_OOD. © 2025, CC BY.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Machine Learning is All You Need: A Simple Token-Based Approach for Effective Code Clone Detection

Machine Learning is All You Need: A Simple Token-Based Appro...

引用

International Conference on Software engineering (ICSE)

作者： Siyue Feng Wenqi Suo Yueming Wu Deqing Zou Yang Liu Hai Jin Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab Jinyinhu Laboratory Wuhan China School of Cyber Science and Engineering HUST Wuhan China Nanyang Technological University Singapore School of Computer Science and Technology HUST Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

As software engineering advances and the code demand rises, the prevalence of code clones has increased. This phenomenon poses risks like vulnerability propagation, underscoring the growing importance of code clone detection techniques. While numerous code clone detection methods have been proposed, they often fall short in real-world code environments. They either struggle to identify code clones effectively or demand substantial time and computational resources to handle complex clones. This paper introduces a code clone detection method namely Toma using tokens and machine learning. Specifically, we extract token type sequences and employ six similarity calculation methods to generate feature vectors. These vectors are then input into a trained machine learning model for classification. To evaluate the effectiveness and scalability of Toma, we conduct experiments on the widely used BigCloneBench dataset. Results show that our tool outperforms token-based code clone detectors and most tree-based clone detectors, demonstrating high effectiveness and significant time savings.

关键词： Codes Scalability Computational modeling Cloning Machine learning Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Impact of Persuasion, Usefulness, and Credibility on User Intent in E-commerce Applications.

引用

Procedia Computer science 2024年 242卷 123-129页

作者： Mariana Aires de Alencar Lucas da Silva Ari Melo Mariano Maíra Rocha Santos Cristian Calderon Collazos Patricia Daza Murillo Teresa Rocio Dalenz Sandoval Jose Loaiza-Torres Department of Production Engineering University of Brasília Brazil Department of Computer Science University of Brasilia Brazil DataLab-Data Lab University of Brasilia Brazil Universidad San Francisco Xavier de Chuquisaca Bolívia

This research aims to present priority actions to improve user experience and fashion consumer design. The Partial Least Square (PLS) technique was used to do this. One hundred thirteen responses were collected for the questionnaire, and an average composite reliability of 0.86 was obtained. The model explained Intention to Use by 37.4%, while Persuasion was explained by 27.9%. Persuasion was the variable that had the most significant impact on intention to use (26.88%), demonstrating that the more persuasive a website or application is, the more likely it is to be used. This is reflected in different segments, as evidenced by campaigns to raise awareness about AIDS and the use of condoms. In addition, usefulness proved to be a crucial factor in increasing persuasiveness (20.11%), indicating that the greater the utilitarian value of the app, the more persuasive it is. Credibility is also essential, influencing both persuasiveness (7.83%) and usefulness (10.16%), with credibility questions focused on verifying whether the honesty of information can influence purchase intent and increase the perception of usefulness and credibility of the website or app.

关键词： PLS-SEM Structural Equation Model UX Design Persuasion Intent of Use E-commerce

来源：评论

学校读者我要写书评

暂无评论

Study of the response of 10B-doped MCP to wide-energy range neutrons from eV to MeV

引用

Nuclear science and Techniques 2024年第8期35卷 132-141页

作者： Qiang Li Li‑Jiao Wang Xiang‑Biao Qiu Jing‑Wen Li Wei Xu Tao Li Ze‑Bin Lin Chang‑Jun Ning Yong‑Hao Chen Rui‑Rui Fan Kang Sun Jing‑Yu Tang Rong Zhang Han‑Tao Jing Bo Mei Qi An Hao‑Fan Bai Jiang‑Bo Bai Jie Bao Ping Cao Qi‑Ping Chen Zhen Chen Zeng‑Qi Cui An‑Chuan Fan Chang‑Qing Feng Fan‑Zhen Feng Ke‑Qing Gao Min‑Hao Gu Chang‑Cai Han Zi‑Jie Han Guo‑Zhu He Yong‑Cheng He Yang Hong Yi‑Wei Hu Han‑Xiong Huang Wei‑Hua Jia Hao‑Yu Jiang Wei Jiang Zhi‑Jie Jiang Zheng‑Yao Jin Ling Kang Bo Li Chao Li Gong Li Jia‑Wen Li Xiao Li Yang Li Jie Liu Rong Liu Shu‑Bin Liu Guang‑Yuan Luan Bin‑Bin Qi Jie Ren Zhi‑Zhou Ren Xi‑Chao Ruan Zhao‑Hui Song Zhi‑Xin Tan Sheng‑Da Tang Peng‑Cheng Wang Zhao‑Hui Wang Zhong‑Wei Wen Xiao‑Guang Wu Xuan Wu Li‑Kun Xie Yi‑Wei Yang Han Yi Yong‑Ji Yu Guo‑Hui Zhang Lin‑Hao Zhang Mo‑Han Zhang Qi‑Wei Zhang Xian‑Peng Zhang Yu‑Liang Zhang Yue Zhang Zhi‑Yong Zhang Mao‑Yuan Zhao Lu‑Ping Zhou Zhi‑Hao Zhou Ke‑Jun Zhu Institute of High Energy Physics Chinese Academy of Sciences(CAS)Beijing 100049China Spallation Neutron Source Science Center Dongguan 523803China State Key Laboratory of Particle Detection and Electronics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China Dongguan Songshan Lake Future School Dongguan 523808China North Night Vision Science&Technology(Nanjing)Research Institute Co.Ltd. Nanjing 211106China Sino‑French Institute of Nuclear Engineering and Technology Sun Yat-sen UniversityZhuhai 519082China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230027China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China Department of Modern Physics University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China USTC Archaeometry Lab University of Science and Technology of ChinaHefei 230026China Northwest Institute of Nuclear Technology Xi’an 710024China University of Chinese Academy of Sciences Beijing 100049China

Neutron-sensitive microchannel plates(nMCPs)have applications in neutron detection,including energy spectrum measurements,neutron-induced cross sections,and neutron imaging.10B-doped MCPs(B-MCPs)have attracted significant attention owing to their potential for exhibiting a high neutron detection efficiency over a large neutron energy *** spatial and temporal resolutions are useful for neutron energy-resolved ***,their practical applications still face many technical *** this study,a B-MCP with 10 mol%10B was tested for its response to wide-energy neutrons from eV to MeV at the Back-n white neutron source at the China Spallation Neutron *** neutron detection efficiency was calibrated at 1 eV,which is approximately 300 times that of an ordinary MCP and indicates the success of 10 B *** factors that caused the reduction in the detection efficiency were simulated and *** neutron energy spectrum obtained using B-MCP was compared with that obtained by other measurement methods,and showed very good consistency for neutron energies below tens of *** response is more complicated at higher neutron energy,at which point the elastic and nonelastic reactions of all nuclides of B-MCP gradually become *** is beneficial for the detection of neutrons,as it compensates for the detection efficiency of B-MCP for high-energy neutrons.

关键词： Neutron radiation image 10B-doped MCP Neutron response Wide-energy range neutrons

来源：评论

学校读者我要写书评

暂无评论

It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation

arXiv

引用

arXiv 2025年

作者： Wu, Jing Wang, Lin Deng, Quanfeng Yu, Chen Zhang, Dong Yan, Bingheng Liu, Fangming National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology China Paderborn University Germany Inspur Data Co. Ltd. China Peng Cheng Laboratory China

Serverless platforms typically adopt an early-binding approach for function sizing, requiring developers to specify an immutable size for each function within a workflow beforehand. Accounting for potential runtime variability, developers must size functions for worst-case scenarios to ensure service-level objectives (SLOs), resulting in significant resource inefficiency. To address this issue, we propose Janus, a novel resource adaptation framework for serverless platforms. Janus employs a late-binding approach, allowing function sizes to be dynamically adapted based on runtime conditions. The main challenge lies in the information barrier between the developer and the provider: developers lack access to runtime information, while providers lack domain knowledge about the workflow. To bridge this gap, Janus allows developers to provide hints containing rules and options for resource adaptation. Providers then follow these hints to dynamically adjust resource allocation at runtime based on real-time function execution information, ensuring compliance with SLOs. We implement Janus and conduct extensive experiments with real-world serverless workflows. Our results demonstrate that Janus enhances resource efficiency by up to 34.7% compared to the state-of-the-art. © 2025, CC BY-NC-ND.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

arXiv

引用

arXiv 2024年

作者： Hu, Youbing Cheng, Yun Lu, Anqi Cao, Zhiqiang Wei, Dawei Liu, Jie Li, Zhijun AIoT Lab. Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland School of Cyber Engineering Xidian University China

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed;if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT’s prowess: it remarkably decreases Deit-S’s FLOPs by 63% and concurrently amplifies throughput twofold. Code of this project is at https://***/edgeai1/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A Grey Wolf Optimization Algorithm with Triangular Community and Crossover Operator for Community Discovery 7

A Grey Wolf Optimization Algorithm with Triangular Community...

引用

7th International Conference on Systems and Informatics, ICSAI 2021

作者： Kang, Yan Huang, Xin Xu, Zhongming Yang, Xuekun Li, Xinyan Software College. Software Engineering of Yunnan University Kunming Data Science and Computing Lab Yunnan China School of Business Travel School of Business and Tourism Management of Yunnan University Kunming Data Science and Computing Lab Yunnan China

ISBN: (纸本)9781665426244

Community discovery under complex networks is a hot discussion issue in network science research. It is very necessary to find a good community structure to study complex networks. At present, many evolutionary algorithms are used for community discovery. However, prior knowledge is not considered for community detection, and full consideration of the network topology can further improve community discovery performance. Therefore, we propose a new algorithm TM-GWO to optimize community discovery. TM-GWO is based on the gray wolf optimization algorithm. It designs a new initialization method and migration-based crossover operator to realize community discovery. The experimental results show that TM-GWO is better than the current Multi-objective evolutionary algorithm. © 2021 IEEE.

关键词： Multiobjective optimization

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：