检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology 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 School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain-Based Revocable Permission Management on CP-ABE Scheme 7th

A Novel Blockchain-Based Revocable Permission Management on ...

引用

7th International Conference on Artificial Intelligence and security, ICAIS 2021

作者： Xv, Qianchuan Song, Yubo Li, Xuan Hu, Aiqun Wang, Junbo Key Laboratory of Computer Networking Technology of Jiangsu Province Nanjing211189 China Purple Mountain Laboratory of Network Communication and Security Nanjing211189 China School of Information Science and Engineering Nanjing211189 China National Mobile Communications Research Laboratory Nanjing211189 China

ISBN: (纸本)9783030786205

Relying on the characteristics of decentralized, tamper-proof, and traceable, blockchain technology has begun to be widely used in permission management. It can be used for access control by using smart contracts to distribute tokens. But also because of the immutability of the blockchain, it cannot dynamically revoke permission. This paper proposed an on-chain user permission management mechanism that could support automatic and active permission revocation. This model proposed an extended CP-ABE chain user permission management model, which realized the permission grant based on user attributes by smart contracts. Furthermore, on this basis, an extended CP-ABE permission revocation mechanism was proposed. The timestamp technology was used to realize the automatic revocation of permission, and the subset coverage algorithm was used to realize the active revocation of permission. A blockchain-based permission distribution model was built, and the permission revocation scheme was introduced into it to conduct experiments. Its performance was tested and analyzed. The experimental results showed that when the number of permission distributions is 1000, the delay is about 5 s. At the same time, the permission change is above 130TPS, which met actual application requirements. © 2021, Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Ranking on Heterogeneous Manifold for Multimodal information Retrieval

Ranking on Heterogeneous Manifold for Multimodal Information...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Zhenkun Jin Xingshi Wan Xin Nie Xinlei Zhou Yuanyuan Yi Gefei Zhou Wuhan Business University Wuhan Research Institute of Posts and Telecommunications Wuhan China Wuhan Research Institute of Posts and Telecommunications Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan China School of Journalism and Information Communication Huazhong University of Science and Technology Wuhan China School of Computer Science & Technology Huazhong University of Science and Technology Wuhan China

In light of recent advancements in Internet of Multimedia Things (IoMT) and 5G technology, both the variety and quantity of data have been rapidly increasing. Consequently, handling zero-shot cross-modal retrieval (ZSCMR) of unlabeled multi-modal data has emerged as a prominent research topic. Early models utilized generative adversarial networks and class embeddings to assist in building a common feature space. However, this approach resulted in a loss of reliability in the feature distributions of individual modalities. In this paper, we propose a method called Ranking on Heterogeneous Manifold (RHM) to address the aforementioned issue. Our model comprises three feature extractors, each dedicated to extracting features from text, images and multimodal data. Subsequently, the relationship structures derived from these feature extractors are employed to construct a heterogeneous manifold. A diffusion process is then conducted on this heterogeneous manifold, ultimately yielding the final ranking scores. Comprehensive experiments demonstrate that the proposed modal has the capability to acquire more effective knowledge representation, thus enhancing the effectiveness of ZSCMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Faster Fully Homomorphic Encryption Implementation with Integer and Floating-point Computing Power of GPUs

Towards Faster Fully Homomorphic Encryption Implementation w...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Guang Fan Fangyu Zheng Lipeng Wan Lili Gao Yuan Zhao Jiankuo Dong Yixuan Song Yuewu Wang Jingqiang Lin State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China School of Cryptography University of Chinese Academy of Sciences Beijing China Department of Computer and Software Nanjing University of Information Science and Technology Nanjing China Ant Group Hangzhou China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Cyber Security University of Science and Technology of China Hefei China

Fully Homomorphic Encryption (FHE) allows computations on encrypted data without knowledge of the plaintext message and currently has been the focus of both academia and industry. However, the performance issue hinders its large-scale application, highlighting the urgent requirements of high-performance FHE *** noticing the tremendous potential of GPUs in the field of cryptographic acceleration, this paper comprehensively investigates how to convert the available computing resources residing in GPUs into FHE workhorses, and implement a full set of low-level and middle-level FHE primitives based on two arithmetic units (i.e., INT32 and FP64 units) with three types of data precision (i.e., INT32, INT64 and FP64). This paper gives a comprehensive evaluation and comparison based on each road-map. Our implementations of fundamental functions outperform the implementations on the same platform by 1.7× to 16.7×. Taking CKKS FHE schemes as a case study, our implementation of homomorphic multiplication achieves 3.2× speedup over the state-of-the-art GPU-based implementation, even considering the difference of platforms. The detailed evaluation and comparison of this paper would offer a vital reference for the follow-up work to choose appropriate underlying arithmetic units and important primitive optimizations in GPU-based FHE implementations.

关键词：

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

A Unified NOMA Framework in Beam-Hopping Satellite communication Systems

arXiv

引用

arXiv 2024年

作者： Zhang, Xuyang Yue, Xinwei Li, Tian Han, Zhihao Wang, Yafei Ding, Yong Liu, Rongke The Key Laboratory of Information and Communication Systems Ministry of Information Industry The Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100101 China The 54th Research Institute of China Electronics Technology Group Corporation Hebei Shijiazhuang050081 China The School of Electronic and Information Engineering Beihang University Beijing100191 China Shenzhen Institution of Beihang University Shenzhen518063 China The Baicells Technologies Co. Ltd Beijing100095 China

This paper investigates the application of a unified non-orthogonal multiple access framework in beam hopping (U-NOMA-BH) based satellite communication systems. More specifically, the proposed U-NOMA-BH framework can be applied to code-domain NOMA based BH (CD-NOMA-BH) and power-domain NOMA based BH (PD-NOMA-BH) systems. To satisfy dynamic-uneven traffic demands, we formulate the optimization problem to minimize the square of discrete difference by jointly optimizing power allocation, carrier assignment and beam scheduling. The non-convexity of the objective function and the constraint condition is solved through Dinkelbach’s transform and variable relaxation. As a further development, the closed-from and asymptotic expressions of outage probability are derived for CD/PD-NOMA-BH systems. Based on approximated results, the diversity orders of a pair of users are obtained in detail. In addition, the system throughput of U-NOMA-BH is discussed in delay-limited transmission mode. Numerical results verify that: i) The gap between traffic requests of CD/PD-NOMA-BH systems appears to be more closely compared with orthogonal multiple access based BH (OMA-BH);ii) The CD-NOMA-BH system is capable of providing the enhanced traffic request and capacity provision;and iii) The outage behaviors of CD/PD-NOMA-BH are better than that of OMA-BH. Copyright © 2024, The Authors. All rights reserved.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

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

Integrated communication and Learned Recognizer with Customized RIS Phases and Sensing Durations

arXiv

引用

arXiv 2025年

作者： Huang, Yixuan Yang, Jie Wen, Chao-Kai Jin, Shi National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China Institute of Communications Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan

Future wireless communication networks are expected to be smarter and more aware of their surroundings, enabling a wide range of context-aware applications. Reconfigurable intelligent surfaces (RISs) are set to play a critical role in supporting various sensing tasks, such as target recognition. However, current methods typically use RIS configurations optimized once and applied over fixed sensing durations, limiting their ability to adapt to different targets and reducing sensing accuracy. To overcome these limitations, this study proposes an advanced wireless communication system that multiplexes downlink signals for environmental sensing and introduces an intelligent recognizer powered by deep learning techniques. Specifically, we design a novel neural network based on the long short-term memory architecture and the physical channel model. This network iteratively captures and fuses information from previous measurements, adaptively customizing RIS phases to gather the most relevant information for the recognition task at subsequent moments. These configurations are dynamically adjusted according to scene, task, target, and quantization priors. Furthermore, the recognizer includes a decision-making module that dynamically allocates different sensing durations, determining whether to continue or terminate the sensing process based on the collected measurements. This approach maximizes resource utilization efficiency. Simulation results demonstrate that the proposed method significantly outperforms state-of-the-art techniques while minimizing the impact on communication performance, even when sensing and communication occur simultaneously. Part of the source code for this paper can be accessed at https://***/kiwi1944/CRISense. Copyright © 2025, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Energy-Age Tradeoff in Status Update communication Systems Based on HARQ 13

Energy-Age Tradeoff in Status Update Communication Systems B...

引用

13th International Conference on Wireless communications and Signal Processing, WCSP 2021

作者： Huang, Jiajie Gong, Jie Zhan, Wen School of Computer Science and Engineering Sun Yat-sen University Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China School of Electronics and Communication Engineering Sun Yat-sen University 518107 China

ISBN: (纸本)9781665407854

The development of the Internet of Things (IoT) has given birth to many real-time applications, which have strict requirements for fresh data. Therefore, a new indicator, age-of-information (AoI), is defined to measure data freshness. On the other hand, the IoT devices such as remote sensors are usually energy-constrained. In this paper, we study the energy-age tradeoff in a state update system. In this system, a source node senses the status data and transmits to a receiver through an error-prone channel. When the transmission fails, the source may either retransmits the existing data to save energy, or sense and transmits new data to reduce the age-of-information. Hybrid Automatic Repeat request (HARQ) and threshold-based retransmission strategy are adopted. Then, we derive the expressions of the average information age and average energy consumption of the system. Finally, the theoretical results are verified via simulations, and the energy-age tradeoff relationship is analyzed. In addition, it is shown that HARQ strategy is more efficient than Automatic Repeat request (ARQ) when the channel condition is very poor. © 2021 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

SALAD: Self-adaptive lightweight anomaly detection for real-time recurrent time series

arXiv

引用

arXiv 2021年

作者： Lee, Ming-Chang Lin, Jia-Chun Gran, Ernst Gunnar Depart. of Information Security and Communication Technology Norwegian University of Science and Technology Gjøvik Norway Depart. of Information Security and Communication Technology Norwegian University of Science and Technology Simula Research Laboratory Gjøvik Norway

Real-world time series data often present recurrent or repetitive patterns and it is often generated in real time, such as transportation passenger volume, network traffic, system resource consumption, energy usage, and human gait. Detecting anomalous events based on machine learning approaches in such time series data has been an active research topic in many different areas. However, most machine learning approaches require labeled datasets, offline training, and may suffer from high computation complexity, consequently hindering their applicability. Providing a lightweight self-adaptive approach that does not need offline training in advance and meanwhile is able to detect anomalies in real time could be highly beneficial. Such an approach could be immediately applied and deployed on any commodity machine to provide timely anomaly alerts. To facilitate such an approach, this paper introduces SALAD, which is a Self-Adaptive Lightweight Anomaly Detection approach based on a special type of recurrent neural networks called Long Short-Term Memory (LSTM). Instead of using offline training, SALAD converts a target time series into a series of average absolute relative error (AARE) values on the fly and predicts an AARE value for every upcoming data point based on short-term historical AARE values. If the difference between a calculated AARE value and its corresponding forecast AARE value is higher than a self-adaptive detection threshold, the corresponding data point is considered anomalous. Otherwise, the data point is considered normal. Experiments based on two real-world open-source time series datasets demonstrate that SALAD outperforms five other state-of-the-art anomaly detection approaches in terms of detection accuracy. In addition, the results also show that SALAD is lightweight and can be deployed on a commodity machine. © 2021, CC BY-NC-ND.

关键词： Anomaly detection

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：