检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Xing Bao Huan Zheng Zhao Zhang Zhengjun Zha Meng Wang School of Information Science and Technology University of Science and Technology of China Hefei China Aerospace Information Research Institute Suzhou China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China

Landmark recognition stands as a prominent classification challenge within the domain of vision and perception, involving the identification and localization of landmarks in images. However, existing landmark recognition methods often fall short in delivering satisfactory performance. A critical issue lies in the lack of simultaneous exploration of local, regional, and global modeling. Intuitively, the local details, regional features, and global structure within an image, especially of a building, significantly contribute to landmark recognition. To address this issue, we propose a novel approach, termed Hierarchical Context Modeling Network (HCMNet), for landmark recognition. In our methodology, we introduce a Hierarchical Context Modeling Block (HCMB) designed with a triplet-branch structure to model image context in a hierarchical manner. These branches consist of the local branch, which leverages a convolutional layer to capture local details, the regional branch focused on extracting regional features through large-kernel asymmetrical convolutional layers, and the global branch aims at encompassing the broader context by incorporating channel attention. To enhance the modeling capacity, we assemble multiple HCMBs into the HCMNet, creating a hierarchical structure. Comprehensive experiments validate the efficacy of the proposed HCMNet for landmark recognition, showcasing its superior performance compared to current methods. The proposed hierarchical context modeling approach proves instrumental in capturing the intricate features essential for accurate landmark recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Large Language Model-Based System and Mitigating Strategies: A Case Study on ChatGPT

引用

Security and Communication Networks 2023年第1期2023卷

作者： Liu, Bowen Xiao, Boao Jiang, Xutong Cen, Siyuan He, Xin Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

Machine learning algorithms are at the forefront of the development of advanced information systems. The rapid progress in machine learning technology has enabled cutting-edge large language models (LLMs), represented by GPT-3 and ChatGPT, to perform a wide range of NLP tasks with a stunning performance. However, research on adversarial machine learning highlights the need for these intelligent systems to be more robust. Adversarial machine learning aims to evaluate attack and defense mechanisms to prevent the malicious exploitation of these systems. In the case of ChatGPT, adversarial induction prompt can cause the model to generate toxic texts that could pose serious security risks or propagate false information. To address this challenge, we first analyze the effectiveness of inducing attacks on ChatGPT. Then, two effective mitigating mechanisms are proposed. The first is a training-free prefix prompt mechanism to detect and prevent the generation of toxic texts. The second is a RoBERTa-based mechanism that identifies manipulative or misleading input text via external detection models. The availability of this method is demonstrated through experiments. © 2023 Bowen Liu et al.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Robustness of LLM-based NLP software via Automated Testing

arXiv

引用

arXiv 2024年

作者： Xiao, Mingxuan Xiao, Yan Ji, Shunhui Cai, Hanbo Xue, Lei Zhang, Pengcheng Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing211100 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

Benefiting from the advancements in LLMs, NLP software has undergone rapid development. Such software is widely employed in various safety-critical tasks, such as financial sentiment analysis, toxic content moderation, and log generation. Unlike traditional software, LLM-based NLP software relies on prompts and examples as inputs. Given the complexity of LLMs and the unpredictability of real-world inputs, quantitatively assessing the robustness of such software is crucial. However, to the best of our knowledge, no automated robustness testing methods have been specifically designed to evaluate the overall inputs of LLM-based NLP software. To this end, this paper introduces the first AutOmated Robustness Testing frAmework, AORTA, which reconceptualizes the testing process into a combinatorial optimization problem. Existing testing methods designed for DNN-based software can be applied to LLM-based software by AORTA, but their effectiveness is limited. To address this, we propose a novel testing method for LLM-based software within AORTA called Adaptive Beam Search. ABS is tailored for the expansive feature space of LLMs and improves testing effectiveness through an adaptive beam width and the capability for backtracking. We successfully embed 18 test methods in the designed framework AORTA and compared the test validity of ABS with three datasets and five threat models. ABS facilitates a more comprehensive and accurate robustness assessment before software deployment, with an average test success rate of 86.138%. Compared to the currently best-performing baseline PWWS, ABS significantly reduces the computational overhead by up to 3441.895 seconds per successful test case and decreases the number of queries by 218.762 times on average. Furthermore, test cases generated by ABS exhibit greater naturalness and transferability. © 2024, CC BY-NC-ND.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Personality Traits for Enhanced Graph Convolutional Networks-Based Social Recommendation Systems

SSRN

引用

SSRN 2023年

作者： Guo, Xiangxing Zhou, Wei Yang, Zhengyi Fu, Cheng Wen, Junhao School of Big Data and Software Engineering Chongqing University Daxuecheng South Rd. 55 Chognqing400044 China Key Laboratory of Dependable Service Computing in Cyber Physical Society MoE Chognqing400030 China

Social recommendation has emerged as a crucial technology for online service platforms, with a growing body of research in recent years. People's varying personalities influence their preferences for items and friends, and neglecting these personalities can result in impure representations that affect recommendation outcomes. In this paper, we propose a Personality-Aware Graph Convolutional Network (PGCN-SRec) model to capture users' preferences based on their personalities. The model first classifies users and their neighbors into personality subgraphs using their representations, and then graph convolution is performed within these subgraphs. User representations from social and interaction subgraphs are fused through a novel fusion module, and layer representations are generated by weighted summation. Experimental results demonstrate that our proposed method significantly improves recommendation performance on the Lastfm and Ciao datasets (by 1\% to 5\%). Furthermore, PGCN-SRec effectively alleviate the oversmoothing problem associated with stacked graph neural networks. Our PyTorch implementation is available at https://***/hsianghsing/PGCN-SRec. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Nodule Classification of CT Images with Attribute Self-guided Graph Convolutional V-Shape Networks 18th

Pulmonary Nodule Classification of CT Images with Attribute ...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Zhang, Xiangbo Wang, Kun Zhang, Xiaohong Huang, Sheng Key Laboratory of Dependabel Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing400044 China The School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9783030891879

Accurate identification and early diagnosis of malignant pulmonary nodules are critical to improving the survival rate of lung cancer patients. Recently, deep learning methods have been proved to be successful in computer-aided diagnosis tasks. However, most advanced research work does not fully utilized valuable attribute prior knowledge for semantic reasoning to guide the network. Therefore, it lacks interpretability and hence is difficult for clinical radiologists to understand and apply. To comprehensively tackle these challenges, we propose a novel Attribute Self-guided Graph Convolutional V-shape Networks (AS-GCVN) for pulmonary nodules classification with steps as follows. We first develop a sub-network for representation learning, which can effectively extract image-level features. Second, we construct a graph convolution V-shape network to model the semantic information of attributes to guide the classification of benign and malignant pulmonary nodules accurately. Moreover, an Attribute Self-guided Feature Enhancement (ASFE) module is proposed to improve the ability of graph semantic reasoning, which can map the image features extracted by the convolutional neural network to attribute features through adaptive learning. Finally, the two sub-networks effectively integrate attribute inference knowledge and representation learning to enable end-to-end training. This way can further improve the interpretability and robustness of pulmonary nodule classification. Extensive experimental results on the LIDC-IDRI dataset demonstrate that our approach obviously outperforms other existing state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A fine-tuned large language model based molecular dynamics agent for code generation to obtain material thermodynamic parameters

引用

Scientific Reports 2025年第1期15卷 1-11页

作者： Shi, Zhuofan Xin, Chunxiao Huo, Tong Jiang, Yuntao Wu, Bowen Chen, Xingyue Qin, Wei Ma, Xinjian Huang, Gang Wang, Zhenyu Jing, Xiang School of Software and Microelectronics Peking University Beijing 102600 China National Key Laboratory of Data Space Technology and System Beijing 100195 China Advanced Institute of Big Data Beijing 100195 China Institute of Information Engineering Chinese Academy of Sciences Beijing 100085 China

In the field of materials science, addressing the complex relationship between the material structure and properties has increasingly involved leveraging the text generation capabilities of AI-generated content (AIGC) models for tasks that include literature mining and data analysis. However, theoretical calculations and code development remain labor-intensive challenges. This paper proposes a novel approach based on text-to-code generation, utilizing large language models to automate the implementation of simulation programs in materials science. The effectiveness of automated code generation and review is validated with thermodynamics simulations based on the LAMMPS software as a foundation. This study introduces Molecular Dynamics Agent (MDAgent), a framework designed to guide large models in automatically generating, executing, and refining simulation code. In addition, a thermodynamic simulation code dataset for LAMMPS was constructed to fine-tune the language model. Expert evaluation scores demonstrate that MDAgent significantly improves the code generation and review capabilities. The proposed approach reduces the average task time by 42.22%, as compared to traditional models, thus highlighting its potential applications in the field of materials science. © The Author(s) 2025.

关键词： Agent LLM Materials science

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

Research on Improved Ant Colony Path Planning Algorithm for Updating Pheromone of Subway Inspection Mobile robot

SSRN

引用

SSRN 2023年

作者： Wang, Lina Yang, Xin Chen, Zeling Wang, Binrui Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China School of Mechanical and Electrical Engineering China Jiliang University Hangzhou310018 China

One enhanced ant colony optimization algorithm is proposed to address the issues related to slow convergence speed and susceptibility to local optima in mobile robot path planning. The algorithm employs several key improvements to achieve these goals. Firstly, the initial path is generated using the artificial potential field method. Pheromones are then added to this initial path to enhance its guidance for ants and expedite the algorithm's convergence during its initial stages. Secondly, an adaptive principle is introduced to optimize the original heuristic function by incorporating the Euclidean distance from optional nodes to the target node. This adjustment further accelerates the algorithm's convergence. Thirdly, enhancements are made to the pheromone update rule, which helps in avoiding local optima and enhances the algorithm's optimization capability. Specifically, if the length of the optimal path remains unchanged for several consecutive iterations, the pheromone concentration on the optimal path is deliberately reduced. Finally, a node optimization strategy is applied to the generated path, eliminating redundant path nodes and effectively shortening the path length. Simulation results demonstrate that the improved algorithm exhibits faster convergence and shorter path lengths compared to the classic ant colony optimization algorithm, resulting in better overall performance. In simple environments, the path length is reduced by 9.19%, and in complex environments, it is reduced by 4.38%. © 2023, The Authors. All rights reserved.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer

arXiv

引用

arXiv 2025年

作者： Chen, Ziyang Zhang, Yongjun Li, Wenting Wang, Bingshu Wu, Yabo Zhao, Yong Chen, C.L. Philip College of Computer Science The State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Information Engineering Guizhou University of Commerce Guiyang550021 China School of Software Northwestern Polytechnical University Xi’an710129 China Key Laboratory of Integrated Microsystems Shenzhen Graduate School Peking University Shenzhen518055 China School of Computer Science and Engineering South China University of Technology Guangzhou510641 China

In light of the advancements in transformer technology, extant research posits the construction of stereo transformers as a potential solution to the binocular stereo matching challenge. However, constrained by the low-rank bottleneck and quadratic complexity of attention mechanisms, stereo transformers still fail to demonstrate sufficient nonlinear expressiveness within a reasonable inference time. The lack of focus on key homonymous points renders the representations of such methods vulnerable to challenging conditions, including reflections and weak textures. Furthermore, a slow computing speed is not conducive to the application. To overcome these difficulties, we present the Hadamard Attention Recurrent Stereo Transformer (HART) that incorporates the following components: 1) For faster inference, we present a Hadamard product paradigm for the attention mechanism, achieving linear computational complexity. 2) We designed a Dense Attention Kernel (DAK) to amplify the differences between relevant and irrelevant feature responses. This allows HART to focus on important details. DAK also converts zero elements to non-zero elements to mitigate the reduced expressiveness caused by the low-rank bottleneck. 3) To compensate for the spatial and channel interaction missing in the Hadamard product, we propose MKOI to capture both global and local information through the interleaving of large and small kernel convolutions. Experimental results demonstrate the effectiveness of our HART. In reflective area, HART ranked 1st on the KITTI 2012 benchmark among all published methods at the time of submission. Code is available at https://***/ ZYangChen/HART. Copyright © 2025, The Authors. All rights reserved.

关键词： Hadamard transforms

来源：评论

学校读者我要写书评

暂无评论

Context decoupling augmentation for weakly supervised semantic segmentation

arXiv

引用

arXiv 2021年

作者： Su, Yukun Sun, Ruizhou Lin, Guosheng Wu, Qingyao School of Software and Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education India School of Computer Science and Engineering Nanyang Technological University Singapore

data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of "aeroplane" may be not only due to the recognition of the object itself, but also its co-occurrence context like "sky", which will cause the model to focus less on the object features. To this end, we present a Context Decoupling Augmentation (CDA) method, to change the inherent context in which the objects appear and thus drive the network to remove the dependence between object instances and contextual information. To validate the effectiveness of the proposed method, extensive experiments on PASCAL VOC 2012 dataset with several alternative network architectures demonstrate that CDA can boost various popular WSSS methods to the new state-of-the-art by a large margin. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：