检索结果-内蒙古大学图书馆

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Xinwei Zhang Tianyuan Zhang Yitong Zhang Shuangcheng Liu School of Computer Science and Engineering Beihang University Beijing China State Key Lab of Software Development Environment Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Deep neural networks are susceptible to attacks from adversarial examples in recent years. Especially, the black-box attacks cause a more serious threat to practical applications. However, while most existing black-box attacks have achieved a high success rate in deceiving models, they have not focused on the stealthiness of adversarial examples, often exhibiting suspicious visual appearances. To address this issue, this paper proposes the Mask Momentum Iterative Attack (MMIA), which introduces a masking mechanism and adopts an optimal perturbation strategy to identify regions of an image most vulnerable to attacks. This approach effectively ensures the transferability and stealthiness of adversarial examples. Simultaneously, by integrating image enhancement techniques and temporal and spatial momentum terms into the iterative process of the attack, we prevent the attack from getting stuck in local optima, further improving the transferability of adversarial examples. To enhance the success rate of black-box attacks, we apply MMIA to a model ensemble using a joint optimization strategy. We demonstrate that adversarially trained models with a strong defense ability are also susceptible to our black-box attacks. We conduct extensive experiments on classification tasks using common vision models, and our results significantly demonstrate the superiority of our method over state-of-the-art approaches when considering both transferability and stealthiness.

关键词： Visualization Fuses Computational modeling Perturbation methods Closed box Pattern recognition Iterative methods

来源：评论

学校读者我要写书评

暂无评论

PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation

PriSTI: A Conditional Diffusion Framework for Spatiotemporal...

引用

International Conference on Data engineering

作者： Mingzhe Liu Han Huang Hao Feng Leilei Sun Bowen Du Yanjie Fu State Key Laboratory of Software Development Environment Beihang University Beijing China Department of Computer Science University of Central Florida USA

Spatiotemporal data mining plays an important role in air quality monitoring, crowd flow modeling, and climate forecasting. However, the originally collected spatiotemporal data in real-world scenarios is usually incomplete due to sensor failures or transmission loss. Spatiotemporal imputation aims to fill the missing values according to the observed values and the underlying spatiotemporal dependence of them. The previous dominant models impute missing values autoregressively and suffer from the problem of error accumulation. As emerging powerful generative models, the diffusion probabilistic models can be adopted to impute missing values conditioned by observations and avoid inferring missing values from inaccurate historical imputation. However, the construction and utilization of conditional information are inevitable challenges when applying diffusion models to spatiotemporal imputation. To address above issues, we propose a conditional diffusion framework for spatiotemporal imputation with enhanced prior modeling, named PriSTI. Our proposed framework provides a conditional feature extraction module first to extract the coarse yet effective spatiotemporal dependencies from conditional information as the global context prior. Then, a noise estimation module transforms random noise to realistic values, with the spatiotemporal attention weights calculated by the conditional feature, as well as the consideration of geographic relationships. PriSTI outperforms existing imputation methods in various missing patterns of different real-world spatiotemporal data, and effectively handles scenarios such as high missing rates and sensor failure. The implementation code is available at https://***/LMZZML/PriSTI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SCPS:A Secure and Copyright-Preserving System for IIoT Based on Hyperledger Fabric 9

SCPS:A Secure and Copyright-Preserving System for IIoT Based...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Peng, Jiahui Li, Chunpei Yuan, Bo Meng, Hongwei Yu, Feng Li, Xianxian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Security GuiLin China Beihang University Development Environment School of Computer Science and Engineering State Key Laboratory of Software Beijing100191 China Xiong'An Intelligent City Innovation Federation Blockchain Lab Beijing China

ISBN: (纸本)9781665407458

Data, a key asset in Industrial Internet of Things(IIoT), has fueled the emergence of a new data trading in-dustry, which can be collected and traded for better development of IIoT. However, copyright protection is not considered in traditional transactions, resulting in the loss of copyright control of the data after the data was sold. A large number of piracy activities will reduce the enthusiasm of data owners to collect data. The solution we proposed was to use blockchain and smart contract to achieve a decentralized and secure copyright protection scheme. The Trusted Execution environment(TEE) helped our system realized the piracy tracking. To be specific, our solution effectively achieves a secure and copyright protection system of IIoT data, we realize the real simulation on Hyperledger Fabric shows the good performance of our system. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

computer-Vision-Based Non-Contact Paste Concentration Measurement*

Computer-Vision-Based Non-Contact Paste Concentration Measur...

引用

Automation in Manufacturing, Transportation and Logistics (ICaMaL), International Conference on

作者： Tailin Liang Zhaolin Yuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Department of Industrial and Systems Engineering Research Institute of Advanced Manufacturing The Hong Kong Polytechnic University Hong Kong China

ISBN: (数字)9798350378658

ISBN: (纸本)9798350378665

For monitoring the paste concentration, existing techniques, such as ultrasonic concentration meters and neutron meters, suffer from radiation hazards and low precision in high concentrations. This paper proposes a novel non-contact concentration measurement method based on deep learning. With the dataset collected by preparing the paste with different concentrations and taking photographs from the paste surface, a convolutional neural network is trained to extract the features from images and predict the concentration. The experiments indicate that the measurement accuracy is close to 88.79 % for the manual stirring paste dataset and 91.42 % for the automatic stirring paste dataset, which are sufficient in industrial applications. As a substitution of traditional concentration measurement instruments, the proposed vision-based concentration measurement method is non-contact and its accuracy is sufficient in industrial applications.

关键词： Meters Deep learning Accuracy Ultrasonic variables measurement Transportation Manuals Feature extraction Surface texture Convolutional neural networks Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Attack End-to-End Autonomous Driving through Module-Wise Noise

arXiv

引用

arXiv 2024年

作者： Wang, Lu Zhang, Tianyuan Han, Yikai Fang, Muyang Jin, Ting Kang, Jiaqi School of Computer Science and Engineering Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China State Key Lab of Software Development Environment Beihang University Beijing China School of Software Beihang University Beijing China

With recent breakthroughs in deep neural networks, numerous tasks within autonomous driving have exhibited remarkable performance. However, deep learning models are susceptible to adversarial attacks, presenting significant security risks to autonomous driving systems. Presently, end-to-end architectures have emerged as the predominant solution for autonomous driving, owing to their collaborative nature across different tasks. Yet, the implications of adversarial attacks on such models remain relatively unexplored. In this paper, we conduct comprehensive adversarial security research on the modular end-to-end autonomous driving model for the first time. We thoroughly consider the potential vulnerabilities in the model inference process and design a universal attack scheme through module-wise noise injection. We conduct large-scale experiments on the full-stack autonomous driving model and demonstrate that our attack method outperforms previous attack methods. We trust that our research will offer fresh insights into ensuring the safety and reliability of autonomous driving systems. © 2024, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Authentic Learning of Machine Learning in Cybersecurity with Portable Hands-on labware: Neural Network Algorithms for Network Denial of Service (DOS) Detection

Authentic Learning of Machine Learning in Cybersecurity with...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Faruk, Md Jobair Hossain Shahriar, Hossain Qian, Kai Lo, Dan Whitman, Michael Cuzzocrea, Alfredo Wu, Fan Clincy, Victor Department of Software Engineering and Game Development Kennesaw State University United States Department of Information Technology Kennesaw State University United States Institute for Cyber Workforce Development Kennesaw State University United States Department Computer Science Kennesaw State University United States IDEA Lab University of Calabria Rende Italy Loria Nancy France Department of Computer Science Tuskegee University United States

ISBN: (纸本)9781665480451

The primary goal of the authentic learning approach is to engage and motivate students in a learning environment that encourages all students in learning. This approach provides students with hands-on experiences in solving real-world security problems. We designed and developed ten learning modules based on 10 cybersecurity cases with different ML solutions. Each learning module consists of pre-lab, lab, and post-lab (Pre/lab/Post) activities. All portable labs are made available on Google Colab for ML to cybersecurity so that students can access and practice these hands-on labs anywhere and anytime without time tedious installation and configuration which will engage students in learning concepts and getting more experience for hands-on problem-solving skills. In this paper, we adopt Neural Network Algorithms for Network Denial of Service (DOS) Detection where we apply the KDDCup 1999 datasets contain a standard set of data to be audited, which includes a wide variety of intrusions simulated in a military network environment. Our primary goal of this lab is to show whether a link is a malicious or safe connection. Our demonstration shows an achieved accuracy of 99.89%. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature Matters: A Framework for Diffusion Model Quantization

arXiv

引用

arXiv 2024年

作者： Huang, Yushi Gong, Ruihao Liu, Xianglong Liu, Jing Li, Yuhang Lu, Jiwen Tao, Dacheng Electrical and Computer Engineering Department Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Software Development Environment Beihang University China Department of Data Science and AI Faculty of IT Monash University Australia Electrical Engineering Department Yale University United States Department of Automation Tsinghua University China School of Computer Science and Engineering Nanyang Technological University Singapore

The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues. However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising. Typically, each time-step is encoded into a hypersensitive temporal feature by several modules. Despite this, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory, as well as reduced compression efficiency. To address these challenges, we introduce a novel quantization framework that includes three strategies: 1) TIB-based Maintenance: Based on our innovative Temporal Information Block (TIB) definition, Temporal Information-aware Reconstruction (TIAR) and Finite Set Calibration (FSC) are developed to efficiently align original temporal features. 2) Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3) Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection between the two maintenance strategies for further disturbance reduction. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets, diffusion models and hardware confirms our superior performance and acceleration. © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Hierarchical state Abstraction Based on Structural Information Principles

arXiv

引用

arXiv 2023年

作者： Zeng, Xianghua Peng, Hao Li, Angsheng Liu, Chunyang He, Lifang Yu, Philip S. State Key Laboratory of Software Development Environment Beihang University China Zhongguancun Laboratory China Didi Chuxing China Computer Science & Engineering Lehigh University United States Department of Computer Science University of Illinois at Chicago United States

state abstraction optimizes decision-making by ignoring irrelevant environmental information in reinforcement learning with rich observations. Nevertheless, recent approaches focus on adequate representational capacities resulting in essential information loss, affecting their performances on challenging tasks. In this article, we propose a novel mathematical Structural Information principles-based state Abstraction framework, namely SISA, from the information-theoretic perspective. Specifically, an unsupervised, adaptive hierarchical state clustering method without requiring manual assistance is presented, and meanwhile, an optimal encoding tree is generated. On each non-root tree node, a new aggregation function and condition structural entropy are designed to achieve hierarchical state abstraction and compensate for sampling-induced essential information loss in state abstraction. Empirical evaluations on a visual gridworld domain and six continuous control benchmarks demonstrate that, compared with five SOTA state abstraction approaches, SISA significantly improves mean episode reward and sample efficiency up to 18.98 and 44.44%, respectively. Besides, we experimentally show that SISA is a general framework that can be flexibly integrated with different representation-learning objectives to improve their performances further. Copyright © 2023, The Authors. 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

Student-Teacher Feature Pyramid Matching for Anomaly Detection 32

Student-Teacher Feature Pyramid Matching for Anomaly Detecti...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Wang, Guodong Han, Shumin Ding, Errui Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Department of Computer Vision Technology Baidu Inc. Beijing China

Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial clues as much as possible. Moreover, we integrate the multi-scale feature matching strategy into the framework, and this hierarchical feature matching enables the student network to receive a mixture of multi-level knowledge from the feature pyramid under better supervision, thus allowing to detect anomalies of various sizes. The difference between feature pyramids generated by the two networks serves as a scoring function indicating the probability of anomaly occurring. Due to such operations, our approach achieves accurate and fast pixel-level anomaly detection. Very competitive results are delivered on the MVTec anomaly detection dataset, superior to the state of the art ones. © 2021. The copyright of this document resides with its authors.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information

arXiv

引用

arXiv 2023年

作者： Zhao, Kun Yang, Bohao Lin, Chenghua Rong, Wenge Villavicencio, Aline Cui, Xiaohui Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Department of Computer Science The University of Sheffield United Kingdom State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China

The long-standing one-to-many issue of the open-domain dialogues poses significant challenges for automatic evaluation methods, i.e., there may be multiple suitable responses which differ in semantics for a given conversational context. To tackle this challenge, we propose a novel learning-based automatic evaluation metric (CMN), which can robustly evaluate open-domain dialogues by augmenting Conditional Variational Autoencoders (CVAEs) with a Next Sentence Prediction (NSP) objective and employing Mutual Information (MI) to model the semantic similarity of text in the latent space. Experimental results on two open-domain dialogue datasets demonstrate the superiority of our method compared with a wide range of baselines, especially in handling responses which are distant to the golden reference responses in semantics. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

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：