检索结果-内蒙古大学图书馆

27th ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2024

作者： Guo, Xiao Zhao, Jianhua Bu, Lei State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China

ISBN: (纸本)9798400705229

Digital filters, a subclass of linear time-invariant systems, are widely used in signal processing and control systems. A digital filter performs mathematical operations on a sampled, discrete-time signal to reduce or enhance certain aspects of that signal. Such a system is implemented by a loop that iterates over an infinite time horizon. At each iteration, a random value is generated as input, and a linear expression is evaluated as output. In control theory, bounded-input, bounded-output (BIBO) stability is a fundamental criterion, which requires that any bounded input to a digital filter yields a bounded output. Correspondingly, at the implementation level, we aim to determine if a specified interval bounds the output of a given filter. However, due to the complexity of digital filters, it is hard for state-of-the-art approaches to make a sound over-approximation of all the possible output values of a filter. In this work, considering the strong connection between poles of digital filters and BIBO stability, we propose a poles-based invariant to over-approximate the output ranges of filters. Initially, we design a decomposition of the iteration of a subclass of filters, based on which we derive a set of inequalities to provide bounds on the output. Subsequently, we generalize this approach to over-approximate the output ranges of general digital filters. Moreover, we split the output value at each iteration into two parts. One is computed precisely by bounded analysis. The other is a new filter that can be analyzed using our invariant. This optimization improves the precision of our approach. Leveraging this approach, we develop a prototype tool for verifying programs related to digital filters and compare it with the state-of-the-art. The results demonstrate that our approach delivers more precise over-approximations in less time for verifying BIBO stability. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Digital filters

来源：评论

学校读者我要写书评

暂无评论

LDCNet: Long-Distance Context Modeling for Large-Scale 3D Point Cloud Scene Semantic Segmentation 24

LDCNet: Long-Distance Context Modeling for Large-Scale 3D Po...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Luo, Shoutong Sun, Zhengxing Wang, Yi Sun, Yunhan Zhu, Chendi State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China

ISBN: (纸本)9798400706868

Large-scale point cloud semantic segmentation is a challenging task in 3D computer vision. A key challenge is how to resolve ambiguities arising from locally high inter-class similarity. In this study, we introduce a solution by modeling long-distance contextual information to understand the scene's overall layout. The context sensitivity of previous methods is typically constrained to small blocks(e.g. 2m x 2m) and cannot be directly extended to the entire scene. For this reason, we propose Long-Distance Context Modeling Network(LDCNet). Our key insight is that keypoints are enough for inferring the layout of a scene. Therefore, we represent the entire scene using keypoints along with local descriptors and model long-distance context on these keypoints. Finally, we propagate the long-distance context information from keypoints back to non-keypoints. This allows our method to model long-distance context effectively. We conducted experiments on six datasets, demonstrating that our approach can effectively mitigate ambiguities. Our method performs well on large, irregular objects and exhibits good generalization for typical scenarios. © 2024 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Grey-box Adversarial Attack on Communication in Multi-agent Reinforcement Learning 22

Grey-box Adversarial Attack on Communication in Multi-agent ...

引用

22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

作者： Ma, Xiao Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Although research on communication in multi-agent reinforcement learning (MARL) has achieved some progress, the vulnerability of the communication mechanism in MARL caused by adversarial communication messages generated by malicious agents has not been well investigated. Existing works about adversarial communication messages in MARL focus on the black-box scenario where the attacker cannot access any model information about the multi-agent system (MAS). But a more practical setting is the grey-box scenario where the attacker can access the model information about its controlled agent. To the best of our knowledge, there has not been any work investigating grey-box attacks on communication in MARL. In this paper, we propose the first grey-box attack method on communication in MARL, which is called victim-simulation based adversarial attack (VSA). At each timestep, the attacker simulates a victim attacked by other regular agents' communication messages and generates adversarial perturbations on its received communication messages. The aggregation of these perturbations is sent by the attacker to the regular agents through communication messages, which will induce non-optimal actions of the regular agents. Experimental results show that VSA can effectively degrade the performance of the MAS on Predator-Prey. The findings in this paper will make researchers aware of the grey-box attack in MARL. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection

引用

computers, Materials & Continua 2023年第6期75卷 5573-5595页

作者： Zhanyang Xu Jianchun Cheng Luofei Cheng Xiaolong Xu Muhammad Bilal School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory Novel Software Technology Nanjing UniversityNanjing210023China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea

Federated learning has been used extensively in business inno-vation scenarios in various *** research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment ***,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise *** proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model ***,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and *** addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global *** results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify ***,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.

关键词： Federated learning feature selection credit risk assessment MSEs

来源：评论

学校读者我要写书评

暂无评论

Improving Open Set Domain Adaptation Using Image-to-Image Translation and Instance-Weighted Adversarial Learning

引用

Journal of computer science & technology 2023年第3期38卷 644-658页

作者：张鸿杰李昂过洁郭延文 State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Google DeepMind Mountain ViewCA 94043U.S.A.

We propose to address the open set domain adaptation problem by aligning images at both the pixel space and the feature *** approach,called Open Set Translation and Adaptation Network(OSTAN),consists of two main components:translation and *** translation is a cycle-consistent generative adversarial network,which translates any source image to the“style”of a target domain to eliminate domain discrepancy in the pixel *** adaptation is an instance-weighted adversarial network,which projects both(labeled)translated source images and(unlabeled)target images into a domain-invariant feature space to learn a prior probability for each target *** learned probability is applied as a weight to the unknown classifier to facilitate the identification of the unknown *** proposed OSTAN model significantly outperforms the state-of-the-art open set domain adaptation methods on multiple public *** experiments also demonstrate that both the image-to-image translation and the instance-weighting framework can further improve the decision boundaries for both known and unknown classes.

关键词： adversarial learning domain adaptation open set translation

来源：评论

学校读者我要写书评

暂无评论

Self-Training with Label-Feature-Consistency for Domain Adaptation 28th

Self-Training with Label-Feature-Consistency for Domain Ad...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Xin, Yi Luo, Siqi Jin, Pengsheng Du, Yuntao Wang, Chongjun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9783031306778

Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to address the domain shift. Recently, self-training has been used in UDA, which exploits pseudo-labels for unlabeled target domains. However, the pseudo-labels can be unreliable due to distribution shifts between domains, severely impairing the model performance. To address this problem, we propose a novel self-training framework-Self-Training with Label-Feature-Consistency (ST-LFC), which selects reliable target pseudo-labels via label-level and feature-level voting consistency principle. The former means target pseudo-labels generated by a source-trained classifier and the latter means the nearest source-class to the target in feature space. In addition, ST-LFC reduces the negative effects of unreliable predictions through entropy minimization. Empirical results indicate that ST-LFC significantly improves over the state-of-the-arts on a variety of benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

RSCache: A Tail Latency Friendly Cache Based on NVMe SSDs 22

RSCache: A Tail Latency Friendly Cache Based on NVMe SSDs

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Lu, Jincheng Cai, Miao Ye, Baoliu Hohai University College of Computer Science and Software Engineering Nanjing China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (纸本)9798331509712

High fan-out requests are prevalent in systems employing multi-tier architectures. These requests are divided into several sub-requests for parallel processing. However, a high fan-out request must await all sub-requests to be completed before returning, but the processing times of sub-requests are unpredictable due to their differences in characteristics, such as data volume and data popularity. Meanwhile, existing SSD-based caches struggle to adjust request processing speeds to ensure timely handling. As a result, some sub-requests are delayed, affecting the overall latency and causing long tail latency *** paper proposes RSCache, a tail latency-friendly cache based on NVMe SSDs. RSCache combines the NVMe Weighted Round-robin (WRR) arbitration mechanism with a priority-based scheduling mechanism to enable differentiated request processing. We propose a fan-out size-based priority assignment strategy along with a latency-aware sub-request sorting method. They collaborate to prioritize sub-requests according to their impacts on tail latency and schedule them to NVMe priority queues with various processing speeds, effectively reducing the processing time variations among sub-requests. In addition, we balance the load across queues to avoid congestion with a novel feedback mechanism. We implement the prototype of RSCache based on SPDK. Our experiments demonstrate that RSCache reduces tail latency by up to 40% and improves throughput by two times compared to state-of-the-art SSD-based cache designs. © 2024 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Capacity Abuse Attack of Deep Learning Models Without Need of Label Encodings

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 814-826页

作者： Luo, Wenjian Zhang, Licai Wu, Yulin Liu, Chuanyi Han, Peiyi Zhuang, Rongfei Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China

In recent years, machine learning (ML) models, especially deep learning models, have become commodities. In this context, data centers which hold a lot of data often buy ML models from ML model providers, train them on their data locally and use the trained models to provide intelligent services. Existing work has shown that there is a risk of data leakage, which could cause incalculable consequences. Even under the black-box condition, there are still some attacks that can steal the private data held by data centers, and the capacity abuse attack (CAA) is the state-of-the-art attack method. CAA attackers steal the training data by labeling malicious samples with the data to be stolen. However, the label encodings are usually mapped into other output forms, such as categories, and it is impossible for the adversary to know the mapping relationship between the form output by the trained model and the label encodings. Without the mapping relationship, CAA becomes invalid. Aiming at the limitation of CAA, this study proposes a novel practical attack method, i.e., capacity abuse attack II (CAAII), which can find the mapping relationship between the output in the arbitrary form returned by the trained model and the values of the stolen data. Experiments are conducted on MNIST, Fashion-MNIST, and CIFAR10 datasets, and experimental results show that no matter what forms are returned by the model, our attack method can always find the mapping relationship and successfully steals the training data. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Injecting Global Context for Multivariate Time Series Forecasting on Variable Subsets

Injecting Global Context for Multivariate Time Series Foreca...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Xin-Yi Yang, Yu-Bin State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9798350368741

Variable Subset Forecasting (VSF) presents a critical challenge where variable availability fluctuates between the training and inference stages. This paper introduces a novel solution to the underexplored VSF problem, seamlessly integrating with existing variate-wise attention architectures. Our approach features two key innovations: (1) a global context-enriched attention mechanism maintaining a holistic data perspective with incomplete variable sets, and (2) a random group mechanism simulating missing data scenarios during training. These innovations effectively address the challenges of maintaining variable correlations under variable stochastic absence and adapting to dynamic input variate without retraining. Experiments demonstrate that our approach improves predictive performance by an average of 16%, with gains of up to 40% in particularly challenging scenarios involving significant variable absence, while adding only a 1% computational overhead. This substantial performance boost, coupled with adaptability to various architectures, positions our approach as a robust solution for real-world MTSF applications facing variable unavailability and domain shifts. © 2025 IEEE.

关键词： Multivariate time series forecasting Variable subset Variate-wise attention

来源：评论

学校读者我要写书评

暂无评论

Inference Retrieval-Augmented Multi-Modal Chain-of-Thoughts Reasoning for Language Models

Inference Retrieval-Augmented Multi-Modal Chain-of-Thoughts ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： He, Qiangqiang Qian, Shuwei Zhang, Jie Wang, Chongjun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9798350368741

Recent advancements in Large Language Models (LLMs) have catalyzed the exploration of Chain of Thought (CoT) approaches, particularly in extending their application to multimodal tasks to enhance reasoning capabilities. However, current studies often fail to fully leverage the inferential capabilities of these models, as they primarily focus on selecting similar questions or images rather than exploring identical inferences, thereby limiting the potential for analogical learning. In this paper, we propose an inference retrieval-augmented method that incorporates two strategies to identify training set examples with inferential processes similar to those of the target problem. Initially, we fine-tune a vanilla model to generate the pseudo-inference relevant to the question, which is then utilized to retrieve analogous examples. Next, we hypothesize that questions sharing similar contexts may share inferences, thus retrieving examples based on similarity in contextual questions. Ultimately, we construct multiple reasoning pathways from the retrieved examples and employ a voting mechanism to determine the most frequent answer. Our method surpasses all few-shot approaches and most supervised methods on the scienceQA dataset, achieving an accuracy of 87.37% with ChatGPT and exceeding the human benchmark in several categories. © 2025 IEEE.

关键词： Chain of Thought Large Language Model Multimodal Reasoning

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：