Query：
学者姓名：刘西蒙
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Federated learning (FL) allows multiple clients to train deep learning models collaboratively while protecting sensitive local datasets. However, FL has been highly susceptible to security for federated backdoor attacks (FBA) through injecting triggers and privacy for potential data leakage from uploaded models in practical application scenarios. FBA defense strategies consider specific and limited attacker models, and a sufficient amount of noise injected can only mitigate rather than eliminate the attack. To address these deficiencies, we introduce a Robust Federated Backdoor Defense Scheme (RFBDS) and Privacy preserving RFBDS (PrivRFBDS) to ensure the elimination of adversarial backdoors. Our RFBDS to overcome FBA consists of amplified magnitude sparsification, adaptive OPTICS clustering, and adaptive clipping. The experimental evaluation of RFBDS is conducted on three benchmark datasets and an extensive comparison is made with state-of-the-art studies. The results demonstrate the promising defense performance from RFBDS, moderately improved by 31.75% similar to 73.75% in clustering defense methods, and 0.03% similar to 56.90% for Non-IID to the utmost extent for the average FBA success rate over MNIST, FMNIST, and CIFAR10. Besides, our privacy-preserving shuffling in PrivRFBDS maintains is 7.83e-5 similar to 0.42x that of state-of-the-art works.
Keyword ：
backdoor defense backdoor defense distributed backdoor attack distributed backdoor attack Federate learning Federate learning heterogeneity data heterogeneity data privacy-preserving privacy-preserving
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Zekai , Yu, Shengxing , Fan, Mingyuan et al. Privacy-Enhancing and Robust Backdoor Defense for Federated Learning on Heterogeneous Data [J]. | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 : 693-707 . |
| MLA | Chen, Zekai et al. "Privacy-Enhancing and Robust Backdoor Defense for Federated Learning on Heterogeneous Data" . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19 (2024) : 693-707 . |
| APA | Chen, Zekai , Yu, Shengxing , Fan, Mingyuan , Liu, Ximeng , Deng, Robert H. . Privacy-Enhancing and Robust Backdoor Defense for Federated Learning on Heterogeneous Data . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 , 693-707 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Users in dynamic spectrum access (DSA) with federated reinforcement learning (FRL) autonomously access channels, avoiding centralized coordination and protecting users' privacy. However, existing FRL-based DSA mechanisms are limited to ideal network states, i.e., assuming that channel states and users' interference relationships are unchanged. Besides, users should upload intermediate results simultaneously for federated aggregation. The above conditions are impractical for mobile users since their network states and locations are unstable. Meanwhile, newly connected users have to train their models through local data with numerous computing resources since global models are unsuitable for them. We propose FRDSA, an FRL-based secure and lightweight channel selection mechanism in DSA for mobile users under dynamic network states. An independent channel selection environment with a virtual group strategy is presented to avoid interference between users under unstable channel states. Furthermore, an asynchronous parameter aggregation method in FRDSA dynamically adjusts the aggregation factors without users simultaneously uploading intermediate results. Simulations based on real trajectory data show that FRDSA significantly reduces approximately 60% interference between mobile users under unstable network states. Newly connected users can directly apply the well-trained global model to access channels autonomously instead of retraining a model, effectively reducing mobile users' computing resource requirements.
Keyword ：
Dynamic spectrum access Dynamic spectrum access federated reinforcement learning federated reinforcement learning location privacy location privacy mobile users mobile users
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Xuewen , You, Zhichao , Liu, Ximeng et al. Federated and Online Dynamic Spectrum Access for Mobile Secondary Users [J]. | IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS , 2024 , 23 (1) : 621-636 . |
| MLA | Dong, Xuewen et al. "Federated and Online Dynamic Spectrum Access for Mobile Secondary Users" . | IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 23 . 1 (2024) : 621-636 . |
| APA | Dong, Xuewen , You, Zhichao , Liu, Ximeng , Guo, Yuanxiong , Shen, Yulong , Gong, Yanmin . Federated and Online Dynamic Spectrum Access for Mobile Secondary Users . | IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS , 2024 , 23 (1) , 621-636 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the absence of well-exposed contents in images, high dynamic range image (HDRI) provides an attractive option that fuses stacked low dynamic range (LDR) images into an HDR image. Existing HDRI methods utilized convolutional neural networks (CNNs) to model local correlations, which can perform well on LDR images with static scenes, but always failed on dynamic scenes where large motions exist. Here we focus on the dynamic scenarios in HDRI, and propose a Query-based Transformer framework, called Q-TrHDRI. To avoid ghosting artifacts induced by moving content fusion, Q-TrHDRI uses Transformer instead of CNNs for feature enhancement and fusion, allowing global interactions across different LDR images. To further improve performance, we investigate comprehensively different strategies of transformers and propose a query-attention scheme for finding related contents across LDR images and a linear fusion scheme for skillfully borrowing complementary contents from LDR images. All these efforts make Q-TrHDRI a simple yet solid transformer-based HDRI baseline. The thorough experiments also validate the effectiveness of the proposed QTrHDRI, where it achieves superior performances over state-of-the-art methods on various challenging datasets.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Bin , Yin, Jia-Li , Chen, Bo-Hao et al. Q-TrHDRI: A Qurey-Based Transformer for High Dynamic Range Imaging with Dynamic Scenes [J]. | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XI , 2024 , 14435 : 301-312 . |
| MLA | Chen, Bin et al. "Q-TrHDRI: A Qurey-Based Transformer for High Dynamic Range Imaging with Dynamic Scenes" . | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XI 14435 (2024) : 301-312 . |
| APA | Chen, Bin , Yin, Jia-Li , Chen, Bo-Hao , Liu, Ximeng . Q-TrHDRI: A Qurey-Based Transformer for High Dynamic Range Imaging with Dynamic Scenes . | PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XI , 2024 , 14435 , 301-312 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
作为一种比较理想的指定验证者签名，变色龙签名(CS)通过在签名算法中嵌入变色龙哈希函数(CHF)对消息进行散列，更简便地解决了签名的2次传递问题。在获得不可传递性的同时，变色龙签名还要求满足不可伪造性、签名者可拒绝性以及不可抵赖性等特性。针对基于大整数分解或离散对数等传统数论难题的CS无法抵御量子计算机攻击，以及随机预言机模型下可证明安全的数字签名方案在实际具体实现中未必安全的问题，该文给出了标准模型下基于格的变色龙签名；进一步地，针对签名者可拒绝性的获得需要耗费其较大的本地存储的问题，给出了标准模型下基于格的无需本地存储的变色龙签名，新方案彻底消除了签名者对本地签名库的依赖，使得签名者能够在不存储原始消息与签名的条件下辅助仲裁者拒绝任意敌手伪造的变色龙签名。特别地，基于格上经典的小整数解问题和差错学习问题，两个方案在标准模型下是可证明安全的。
Keyword ：
不可传递性 不可传递性 变色龙签名 变色龙签名 无需本地存储 无需本地存储 标准模型 标准模型 格 格
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张彦华 , 陈岩 , 刘西蒙 et al. 标准模型下基于格的变色龙签名方案 [J]. | 电子与信息学报 , 2024 : 1-8 . |
| MLA | 张彦华 et al. "标准模型下基于格的变色龙签名方案" . | 电子与信息学报 (2024) : 1-8 . |
| APA | 张彦华 , 陈岩 , 刘西蒙 , 尹毅峰 , 胡予濮 . 标准模型下基于格的变色龙签名方案 . | 电子与信息学报 , 2024 , 1-8 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to enormous computing and storage overhead for well-trained Deep Neural Network (DNN) models, protecting the intellectual property of model owners is a pressing need. As the commercialization of deep models is becoming increasingly popular, the pre-trained models delivered to users may suffer from being illegally copied, redistributed, or abused. In this paper, we propose DeepDIST, the first end-to-end secure DNNs distribution framework in a black-box scenario. Specifically, our framework adopts a dual-level fingerprint (FP) mechanism to provide reliable ownership verification, and proposes two equivalent transformations that can resist collusion attacks, plus a newly designed similarity loss term to improve the security of the transformations. Unlike the existing passive defense schemes that detect colluding participants, we introduce an active defense strategy, namely damaging the performance of the model after the malicious collusion. The extensive experimental results show that DeepDIST can maintain the accuracy of the host DNN after embedding fingerprint conducted for true traitor tracing, and is robust against several popular model modifications. Furthermore, the anti-collusion effect is evaluated on two typical classification tasks (10-class and 100-class), and the proposed DeepDIST can drop the prediction accuracy of the collusion model to 10% and 1% (random guess), respectively.
Keyword ：
anti-collusion anti-collusion Deep neural networks Deep neural networks digital fingerprinting digital fingerprinting digital watermarking digital watermarking
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Hang , Li, Xibin , Wang, Huaxiong et al. DeepDIST: A Black-Box Anti-Collusion Framework for Secure Distribution of Deep Models [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (1) : 97-109 . |
| MLA | Cheng, Hang et al. "DeepDIST: A Black-Box Anti-Collusion Framework for Secure Distribution of Deep Models" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34 . 1 (2024) : 97-109 . |
| APA | Cheng, Hang , Li, Xibin , Wang, Huaxiong , Zhang, Xinpeng , Liu, Ximeng , Wang, Meiqing et al. DeepDIST: A Black-Box Anti-Collusion Framework for Secure Distribution of Deep Models . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (1) , 97-109 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Outsourcing storage has emerged as an effective solution to manage the increasing volume of data. With the popularity of pay-as-you-go payment models in outsourcing storage, data auditing schemes that prioritize timeliness can be valuable evidence for elastic bill settlement. Unfortunately, existing data auditing schemes do not sufficiently consider timeliness during auditing. Furthermore, practical data auditing schemes should have the capability to check the integrity of scalable data. In this paper, we propose a blockchain-based dynamic data auditing scheme with strong timeliness to ensure that data stored in outsourcing storage systems remain intact. Our scheme encapsulates timestamps into homomorphic verifiable tags to simultaneously check data integrity and timestamp validity. To achieve dynamicity, we utilize the Merkle hash tree to store the tags, allowing for block-level dynamic operations. Additionally, by leveraging the transparency, non-repudiation, and tamper resistance of blockchain technology, we design a blockchain-based data auditing framework to prevent malicious behavior from all entities. We then formally prove the soundness and privacy of our scheme. Finally, we conduct theoretical analysis and experimental evaluation to demonstrate that the performance of our scheme is of acceptable efficiency to existing works in terms of computation cost, communication overhead, and storage overhead.
Keyword ：
blockchain blockchain dynamic data auditing dynamic data auditing Outsourcing storage Outsourcing storage timeliness timeliness
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Chuan , Xuan, Haojun , Wu, Tong et al. Blockchain-Based Dynamic Time-Encapsulated Data Auditing for Outsourcing Storage [J]. | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 : 1979-1993 . |
| MLA | Zhang, Chuan et al. "Blockchain-Based Dynamic Time-Encapsulated Data Auditing for Outsourcing Storage" . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19 (2024) : 1979-1993 . |
| APA | Zhang, Chuan , Xuan, Haojun , Wu, Tong , Liu, Ximeng , Yang, Guomin , Zhu, Liehuang . Blockchain-Based Dynamic Time-Encapsulated Data Auditing for Outsourcing Storage . | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , 2024 , 19 , 1979-1993 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Outsourcing data to the cloud has become prevalent, so Searchable Symmetric Encryption (SSE), one of the methods for protecting outsourced data, has arisen widespread interest. Moreover, many novel technologies and theories have emerged, especially for the attacks on SSE and privacy-preserving. But most surveys related to SSE concentrate on one aspect (e.g., single keyword search, fuzzy keyword search) or lack in-depth analysis. Therefore, we revisit the existing work and conduct a comprehensive analysis and summary. We provide an overview of state-of-the-art in SSE and focus on the privacy it can protect. Generally, (1) we study the work of the past few decades and classify SSE based on query expressiveness. Meanwhile, we summarize the existing schemes and analyze their performance on efficiency, storage space, index structures, and so on.; (2) we complement the gap in the privacy of SSE and introduce in detail the attacks and the related defenses; (3) we discuss the open issues and challenges in existing schemes and future research directions. We desire that our work will help novices to grasp and understand SSE comprehensively. We expect it can inspire the SSE community to discover more crucial leakages and design more efficient and secure constructions.
Keyword ：
cloud security cloud security privacy-preserving privacy-preserving Searchable encryption Searchable encryption
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Feng , Ma, Jianfeng , Miao, Yinbin et al. A Survey on Searchable Symmetric Encryption [J]. | ACM COMPUTING SURVEYS , 2024 , 56 (5) . |
| MLA | Li, Feng et al. "A Survey on Searchable Symmetric Encryption" . | ACM COMPUTING SURVEYS 56 . 5 (2024) . |
| APA | Li, Feng , Ma, Jianfeng , Miao, Yinbin , Liu, Ximeng , Ning, Jianting , Deng, Robert H. . A Survey on Searchable Symmetric Encryption . | ACM COMPUTING SURVEYS , 2024 , 56 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, evolutionary computation (EC) has experienced significant advancements due to the integration of machine learning, distributed computing, and big data technologies. These developments have led to new research avenues in EC, such as distributed EC and surrogate-assisted EC. While these advancements have greatly enhanced the performance and applicability of EC, they have also raised concerns regarding privacy leakages, specifically the disclosure of optimal results and surrogate models. Consequently, the combination of evolutionary computation and privacy protection becomes an increasing necessity. However, a comprehensive exploration of privacy concerns in evolutionary computation is currently lacking, particularly in terms of identifying the object, motivation, position, and method of privacy protection. To address this gap, this paper aims to discuss three typical optimization paradigms, namely, centralized optimization, distributed optimization, and data-driven optimization, to characterize optimization modes of evolutionary computation and proposes BOOM (i.e., oBject, mOtivation, pOsition, and Method) to sort out privacy concerns related to evolutionary computation. In particular, the centralized optimization paradigm allows clients to outsource optimization problems to a centralized server and obtain optimization solutions from the server. The distributed optimization paradigm exploits the storage and computational power of distributed devices to solve optimization problems. On the other hand, the data-driven optimization paradigm utilizes historical data to address optimization problems without explicit objective functions. Within each of these paradigms, BOOM is used to characterize the object and motivation of privacy protection. Furthermore, this paper discuss the potential privacy-preserving technologies that strike a balance between optimization performance and privacy guarantees. Finally, this paper outlines several new research directions for privacy-preserving evolutionary computation.
Keyword ：
Centralized optimization Centralized optimization data-driven optimization data-driven optimization Data privacy Data privacy distributed optimization distributed optimization evolutionary computation evolutionary computation Evolutionary computation Evolutionary computation Linear programming Linear programming Machine learning Machine learning Object recognition Object recognition Privacy Privacy privacy protection privacy protection Servers Servers
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Bowen , Chen, Wei-Neng , Li, Xiaoguo et al. When Evolutionary Computation Meets Privacy [J]. | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE , 2024 , 19 (1) : 66-74 . |
| MLA | Zhao, Bowen et al. "When Evolutionary Computation Meets Privacy" . | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 19 . 1 (2024) : 66-74 . |
| APA | Zhao, Bowen , Chen, Wei-Neng , Li, Xiaoguo , Liu, Ximeng , Pei, Qingqi , Zhang, Jun . When Evolutionary Computation Meets Privacy . | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE , 2024 , 19 (1) , 66-74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this article, we propose a secure fine-grained task allocation scheme with bilateral access control (FTA-BAC) for intelligent transportation systems. To enhance the security, we formulate bilateral access control in task allocation, by adopting the matchmaking encryption (ME) to encrypt the task requirements/interests for secure task matching. In this way, both task requesters and workers can specify their match policies simultaneously, without revealing their sensitive information (i.e., attributes and geographical location). To realize fine-grained task allocation, we use a linear integer secret sharing (LISS) scheme to represent task requirements/interests, supporting the AND/OR operation on match policies. To further improve the efficiency, we design a delegation mechanism to reduce the computation burden on resource-limited end devices, by diverting the high-frequency matching operations to edge nodes. Then, we prove the security of FTA-BAC under formally defined security model. Finally, we analyze the performance of FTA-BAC through theoretical analysis and experimental evaluation, demonstrating that FTA-BAC can provide practical task allocation for intelligent transportation systems compared with the state-of-the-art works. © 2014 IEEE.
Keyword ：
Access control Access control Cryptography Cryptography Edge computing Edge computing Intelligent systems Intelligent systems Job analysis Job analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Tong , Ma, Xiaochen , Zhang, Chuan et al. Toward Fine-Grained Task Allocation With Bilateral Access Control for Intelligent Transportation Systems [J]. | IEEE Internet of Things Journal , 2024 , 11 (8) : 14814-14828 . |
| MLA | Wu, Tong et al. "Toward Fine-Grained Task Allocation With Bilateral Access Control for Intelligent Transportation Systems" . | IEEE Internet of Things Journal 11 . 8 (2024) : 14814-14828 . |
| APA | Wu, Tong , Ma, Xiaochen , Zhang, Chuan , Liu, Ximeng , Yang, Guomin , Zhu, Liehuang . Toward Fine-Grained Task Allocation With Bilateral Access Control for Intelligent Transportation Systems . | IEEE Internet of Things Journal , 2024 , 11 (8) , 14814-14828 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Federated learning (FL) provides a learning framework without participants sharing local raw data, but individual privacy is still at risk of disclosure through attacking the trained models. Due to the strong privacy guarantee, differential privacy (DP) is widely applied to FL to avoid privacy leakage. Traditional private learning adds noise directly to the gradients. The continuous accumulated noise on parameter models severely impairs learning effectiveness. To solve this problem, we introduce the idea of differentially private continuous data release (DPCR) into FL and propose an FL framework based on DPCR (FL-DPCR). Meanwhile, our proposed Equivalent Aggregation Theorem demonstrates that DPCR effectively reduces the overall error added to parameter models and improves FL's accuracy. To improve FL-DPCR's learning effectiveness, we introduce Matrix Mechanism to construct a release strategy and design a binary-indexed-tree (BIT) based DPCR model for Gaussian mechanism (BCRG). By solving a complex nonlinear programming problem with negative exponents, BCRG achieves optimal release accuracy efficiently. Besides, we exploit the residual privacy budget to boost the accuracy further and propose an advanced BCRG version (ABCRG). Our experiments show that, compared to traditional FL with DP, our achievements improve the accuracy with gains ranging from $3.4\%$ on FMNIST to $65.7\%$ on PAMAP2. IEEE
Keyword ：
Artificial intelligence Artificial intelligence Binary Indexed Tree Binary Indexed Tree Biomedical imaging Biomedical imaging Computational modeling Computational modeling Continuous Data Release Continuous Data Release Data models Data models Differential privacy Differential privacy Differential Privacy Differential Privacy Federated learning Federated learning Matrix Mechanism Matrix Mechanism Privacy Privacy Security Security
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cai, J. , Liu, X. , Ye, Q. et al. A Federated Learning Framework Based on Differentially Private Continuous Data Release [J]. | IEEE Transactions on Dependable and Secure Computing , 2024 , 21 (5) : 1-16 . |
| MLA | Cai, J. et al. "A Federated Learning Framework Based on Differentially Private Continuous Data Release" . | IEEE Transactions on Dependable and Secure Computing 21 . 5 (2024) : 1-16 . |
| APA | Cai, J. , Liu, X. , Ye, Q. , Liu, Y. , Wang, Y. . A Federated Learning Framework Based on Differentially Private Continuous Data Release . | IEEE Transactions on Dependable and Secure Computing , 2024 , 21 (5) , 1-16 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
