检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai 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 School of Computer Science and Technology 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 China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

arXiv

引用

arXiv 2022年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng The School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China The School of Computer Science Faculty of Engineering The University of Sydney Sydney Australia The College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue Singapore639798 Singapore

Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely PANDA) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) our proposed metric works well to predict the prompt transferability;2) our PANDA consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes;3) with our PANDA approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios. We have publicly released our code in https://***/WHU-ZQH/PANDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai 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 School of Computer Science and Technology 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 China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

BuildSenSys: Reusing building sensing data for traffic prediction with cross-domain learning

arXiv

引用

arXiv 2020年

作者： Fan, Xiaochen Xiang, Chaocan Chen, Chao Yang, Panlong Gong, Liangyi Song, Xudong Nanda, Priyadarsi He, Xiangjian School of Electrical and Data Engineering Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China College of Computer Science Chongqing University Chongqing400044 China School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230026 China School of Software BNRist Tsinghua University Beijing100084 China

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperf

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Noncontact Doppler Radar-based Heart Rate Detection on the SVD and ANC

Noncontact Doppler Radar-based Heart Rate Detection on the S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qiuxia Shi Bin Hu Fuze Tian Qinglin Zhao Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University School of Computer and Communication Lanzhou University of Technology Ministry of Education Key Laboratory of Special Functional Materials and Structural Design (Lanzhou University) Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors Chinese Academy of Sciences Engineering Research Center of Open Source Software and Real-Time System(Lanzhou University) Ministry of Education Key Laboratory of Special Functional Materials and Structural Design Ministry of Education Lanzhou University Lanzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

In the Doppler biological radar-based applications of noncontact measurement of vital signs, effectively extracting heartbeat information from weak thoracic mechanical motion is an important problem to be solved. This study is aimed at extracting heartbeat signal via the technology combined with Short Time Fourier Transform (STFT), Singular Value Decomposition (SVD) and Adaptive Noise Canceller (ANC) from radar recording. The simulated data and the data collected by Doppler radar biosensor realized in laboratory are employed to validate the proposed method. The results show that the proposed method has the ability of detection for the heart rate and heart rate variability indexes in rest state, it has certain advantages in time-consuming and detection accuracy. Therefore, the current method provides another way to process vital sign signals recorded by Doppler radar.

关键词： Biomedical measurement Noise cancellation Time measurement Doppler radar Recording Doppler effect Biosensors

来源：评论

学校读者我要写书评

暂无评论

Package of the vector math library based on the sunway processor

引用

Ruan Jian Xue Bao/Journal of software 2014年 25卷 70-79页

作者： Xie, Qing-Chun Zhang, Yun-Quan Li, Yan Pang, Ren-Bo Wu, Zai-Long Lu, Yong-Quan Gao, Peng-Dong High Performance Computing Center Communication University of China Beijing100024 China Laboratory of Parallel Computing Institute of Software The Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Computer Architecture Institute of Computing Technology The Chinese Academy of Sciences Beijing100190 China Department of Computer and Network National Marine Environmental Forecasting Center Beijing100081 China School of Information Sceience and Technology The Ocean University of China Qingdao266100 China

This paper first introduces the SIMD (single instruction multiple data) extension technology and presents three ways to use SIMD instructions. It is considered that calling the third party library, which is optimized for the target platform by using those instructions, is the best way to benefit the developers. Next, it introduces the China-developed SW-1600 CPU, and a software package called SW-VML, which consists of many mathematical functions, by using the SIMD extension technology. In order to solve the additional overhead caused by unaligned address access and transformation between vector and scalar array, the paper provides some performance optimized methods, such as aligned address access, simplifying vector condition branch and loop unrolling. An upgrade to SW-VML is also offered to support multi-thread with OpenMP. Finally, functions in the package are tested using arrays of different sizes on SW-1600, and the test results show that high performance is achieved with the technology of the SIMD vectorization. Compared with the traditional methods of the scalar calculation, the average speedup is up to 2.06. The performance speedup of package using 4 threads is up to 2.26 compared to using a single thread. SW-VML is a common vector function package for domestic Sunway processor series, and it can be used as a basic toolkit which is beneficial to high performance computing on Sunway platform. ©2014 ISCAS.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

MISA: UNVEILING THE VULNERABILITIES IN SPLIT FEDERATED LEARNING

arXiv

引用

arXiv 2023年

作者： Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Li, Minghui Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology 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 Information and Communication Technology Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users' devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of robustness. In this paper, we present a novel poisoning attack known as MISA. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

arXiv

引用

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

A Quantum Probability Driven Framework for Joint Multi-Modal Sarcasm, Sentiment and Emotion Analysis

arXiv

引用

arXiv 2023年

作者： Liu, Yaochen Zhang, Yazhou Song, Dawei School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China School of Computing and Communications The Open University Walton Hall United Kingdom School of Nursing The Hong Kong Polytechnic University Hong Kong Ministry of Education China Artificial Intelligence Laboratory China Mobile Communication Group Tianjin Co. Ltd. China State Key Lab. for Novel Software Technology Nanjing University Nanjing China Zhengzhou University of Light Industry China

Sarcasm, sentiment, and emotion are three typical kinds of spontaneous affective responses of humans to external events and they are tightly intertwined with each other. Such events may be expressed in multiple modalities (e.g., linguistic, visual and acoustic), e.g., multi-modal conversations. Joint analysis of humans’ multi-modal sarcasm, sentiment, and emotion is an important yet challenging topic, as it is a complex cognitive process involving both cross-modality interaction and cross-affection correlation. From the probability theory perspective, cross-affection correlation also means that the judgments on sarcasm, sentiment, and emotion are incompatible. However, this exposed phenomenon cannot be sufficiently modelled by classical probability theory due to its assumption of compatibility. Neither do the existing approaches take it into consideration. In view of the recent success of quantum probability (QP) in modeling human cognition, particularly contextual incompatible decision making, we take the first step towards introducing QP into joint multi-modal sarcasm, sentiment, and emotion analysis. Specifically, we propose a QUantum probabIlity driven multi-modal sarcasm, sEntiment and emoTion analysis framework, termed QUIET. Extensive experiments on two datasets and the results show that the effectiveness and advantages of QUIET in comparison with a wide range of the state-of-the-art baselines. We also show the great potential of QP in multi-affect analysis. Copyright © 2023, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2023年

作者： Shi, Zhaoyuan Lu, Huabing Xie, Xianzhong Yang, Helin Huang, Chongwen Cai, Jun Ding, Zhiguo The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing China The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian116024 China Chongqing Key Lab of Computer networks and Communication Technology Chongqing University of Posts and Telecommunications Chongqing China The Department of Information and Communication Engineering School of Informatics Xiamen University Xiamen361005 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada The Department of Electrical Engineering Princeton University PrincetonNJ08544 United States The School of Electrical and Electronic Engineering The University of Manchester Manchester United Kingdom

An active reconfigurable intelligent surface (RIS)-aided multi-user downlink communication system is investigated, where non-orthogonal multiple access (NOMA) is employed to improve spectral efficiency, and the active RIS is powered by energy harvesting (EH). The problem of joint control of the RIS’s amplification matrix and phase shift matrix is formulated to maximize the communication success ratio with considering the quality of service (QoS) requirements of users, dynamic communication state, and dynamic available energy of RIS. To tackle this non-convex problem, a cascaded deep learning algorithm namely long short-term memory-deep deterministic policy gradient (LSTM-DDPG) is designed. First, an advanced LSTM based algorithm is developed to predict users’ dynamic communication state. Then, based on the prediction results, a DDPG based algorithm is proposed to joint control the amplification matrix and phase shift matrix of the RIS. Finally, simulation results verify the accuracy of the prediction of the proposed LSTM algorithm, and demonstrate that the LSTM-DDPG algorithm has a significant advantage over other benchmark algorithms in terms of communication success ratio performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

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：