检索结果-内蒙古大学图书馆

Distributional Black-Box Model Inversion Attack with Multi-Agent Reinforcement Learning

IEEE Transactions on Information Forensics and security 2025年

作者： Bao, Huan Wei, Kaimin Wu, Yongdong Qian, Jin Deng, Robert H. Jinan University College of Cyber Security Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangdong Institute of Smart Education Guangzhou510632 China Singapore Management University School of Information Systems 178902 Singapore

Model Inversion (MI) attacks based on Generative Adversarial Networks (GAN) aim to recover private training data from complex deep learning models by searching codes in the latent space. However, this method merely searches in a deterministic latent space, resulting in suboptimal latent codes. Additionally, existing distributional MI schemes assume that an attacker can access the structures and parameters of the target model, which is not always feasible in practice. To address these limitations, this paper proposes a novel Distributional Black-Box Model Inversion (DBB-MI) attack by constructing a probabilistic latent space for searching private data. Specifically, DBB-MI does not require the target model’s parameters or specialized GAN training. Instead, it identifies the latent probability distribution by integrating the output of the target model with multi-agent reinforcement learning techniques. Then, it randomly selects latent codes from the latent probability distribution to uncover private data. As the latent probability distribution closely mirrors the target privacy data in the latent space, the recovered data effectively leaks the privacy of the target model’s training samples. Extensive experiments conducted on diverse datasets and networks demonstrate that our DBB-MI outperforms state-of-the-art MI attacks in terms of attack accuracy, K-nearest neighbor feature distance, and peak signal-to-noise ratio. © 2005-2012 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Improved lattice-based CCA2-secure PKE in the standard model

引用

Science China(Information Sciences) 2020年第8期63卷 147-168页

作者： Jiang ZHANG Yu YU Shuqin FAN Zhenfeng ZHANG State Key Laboratory of Cryptology Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Jinan University Department of Computer Science and Engineering Shanghai Jiao Tong University Trusted Computing and Information Assurance Laboratory Institute of SoftwareChinese Academy of Sciences

Based on the identity-based encryption(IBE) from lattices by Agrawal et al.(Eurocrypt’10),Micciancio and Peikert(Eurocrypt’12) presented a CCA1-secure public-key encryption(PKE), which has the best known efficiency in the standard model and can be used to obtain a CCA2-secure PKE from lattices by using the generic BCHK transform(SIAM J Comput, 2006) with a cost of introducing extra overheads to both computation and storage for the use of other primitives such as signatures and commitments. In this paper, we propose a more efficient standard model CCA2-secure PKE from lattices by carefully combining a different message encoding(which encodes the message into the most significant bits of the LWE’s "secret term") with several nice algebraic properties of the tag-based lattice trapdoor and the LWE problem(such as unique witness and additive homomorphism). Compared to the best known lattice-based CCA1-secure PKE in the standard model due to Micciancio and Peikert(Eurocrypt’12), we not only directly achieve the CCA2-security without using any generic transform(and thus do not use signatures or commitments), but also reduce the noise parameter roughly by a factor of 3. This improvement makes our CCA2-secure PKE more efficient in terms of both computation and storage. In particular, when encrypting a 256-bit(respectively,512-bit) message at 128-bit(respectively, 256-bit) security, the ciphertext size of our CCA2-secure PKE is even 33%–44%(respectively, 36%–46%) smaller than that of their CCA1-secure PKE.

关键词： lattice public-key encryption chosen ciphertext security standard model

来源：评论

学校读者我要写书评

暂无评论

Aggregation-based dual heterogeneous task allocation in spatial crowdsourcing

引用

Frontiers of Computer Science 2024年第6期18卷 215-227页

作者： Xiaochuan LIN Kaimin WEI Zhetao LI Jinpeng CHEN Tingrui PEI College of Information Science and Technology&Cyberspace Security Jinan UniversityGuangzhou 510632China National&Local Joint Engineering Research Center of Network Security Detection and Protection Technology Guangzhou 510632China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou 510632China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Spatial crowdsourcing(SC)is a popular data collection paradigm for numerous *** the increment of tasks and workers in SC,heterogeneity becomes an unavoidable difficulty in task *** researches only focus on the single-heterogeneous task ***,a variety of heterogeneous objects coexist in real-world SC *** dramatically expands the space for searching the optimal task allocation solution,affecting the quality and efficiency of data *** this paper,an aggregation-based dual heterogeneous task allocation algorithm is put *** investigates the impact of dual heterogeneous on the task allocation problem and seeks to maximize the quality of task completion and minimize the average travel *** problem is first proved to be ***,a task aggregation method based on locations and requirements is built to reduce task ***,a time-constrained shortest path planning is also developed to shorten the travel distance in a *** that,two evolutionary task allocation schemes are ***,extensive experiments are conducted based on real-world datasets in various *** with baseline algorithms,our proposed schemes enhance the quality of task completion by up to 25% and utilize 34% less average travel distance.

关键词： task allocation aggregation shortest path dual heterogeneous spatial crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Cancer classification with data augmentation based on generative adversarial networks

引用

Frontiers of Computer Science 2022年第2期16卷 69-79页

作者： Kaimin WEI Tianqi LI Feiran HUANG Jinpeng CHEN Zefan HE College of Information Science and Technology Jinan UniversityGuangzhou 510632China Guangdong Key Laboratory of Data Security and Privacy Protection Guangzhou 510632China School of Software Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

Accurate diagnosis is a significant step in cancer *** learning can support doctors in prognosis decision-making,and its performance is always weakened by the high dimension and small quantity of genetic ***,deep learning can effectively process the high dimensional data with ***,the problem of inadequate data remains unsolved and has lowered the performance of deep *** end it,we propose a generative adversarial model that uses non target cancer data to help target generator *** use the reconstruction loss to further stabilize model training and improve the quality of generated *** also present a cancer classification model to optimize classification *** results prove that mean absolute error of cancer gene made by our model is 19.3%lower than DC-GAN,and the classification accuracy rate of our produced data is higher than the data created by *** for the classification model,the classification accuracy of our model reaches 92.6%,which is 7.6%higher than the model without any generated data.

关键词： data mining cancer data analysis deep learning generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Iterative Bounded Distance Decoding with Random Flipping for Product-Like Codes

引用

IEEE Transactions on Communications 2024年第5期73卷 2864-2875页

作者： Li, Guorong Wang, Shiguo Zhao, Shancheng Jinan University National and Local Joint Research Center of Network Security Detection and Protection Technology College of Information Science and Technology Guangzhou510632 China Guangdong Key Laboratory of Data Security and Privacy Preserving The Guangzhou Key Laboratory of Data Security and Privacy Preserving Guangzhou510632 China Changsha University of Science and Technology Computer and Communication Engineering Institute Changsha410114 China

Product-like codes are widely used in high-speed communication systems since they can be decoded with low-complexity hard decision decoders (HDDs). To meet the growing demand of data rates, enhanced HDDs are required. In this paper, we propose a novel soft-aided HDD (SA-HDD), termed iterative bounded distance decoding with random flipping (iBDD-RF), for product-like codes. In iBDD-RF, the soft reliability of a bit is a weighted sum of the output of bounded distance decoder (BDD) and the channel log-likelihood ratio (LLR). When the amplitude of the soft reliability of a bit is less than a given threshold, it is flipped with a given probability. This random flipping may make the decoder escape from the local optimum. To optimize the threshold and the flipping probability, we derive the density evolution (DE) equations of iBDD-RF for product codes (PCs) and staircase codes (SCs). Our extensive numerical results show that iBDD-RF outperforms iBDD with scaled reliability (iBDD-SR) over the binary-input additive white Gaussian noise (Bi-AWGN) channel. Particularly, for a PC with (255,239,2) Bose-Chaudhuri-Hocquenghem (BCH) code and an SC with (254,230,3) BCH code, iBDD-RF performs about 0.25 dB and 0.28 dB better than iBDD-SR, respectively. © 2024 IEEE.

关键词： Optical fiber communication

来源：评论

学校读者我要写书评

暂无评论

An identity-based anonymous signcryption for vehicular ad hoc networks 2nd

An identity-based anonymous signcryption for vehicular ad ho...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Lu, Yong Yang, Huijie School of Management Science and Engineering Nanjing University of Information Science and Technology Nanjing China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou China

ISBN: (纸本)9789811561122

The vehicular ad hoc networks (VANETs) can share information of vehicles’ location, speed and route within a certain range by interconnecting vehicles, roadside units (RSU) and the cloud. As people’s daily traffic tools, vehicles reflect users’ daily routines and other privacy. Therefore, privacy protection is very critical in VANETs. However, in the existing schemes, a user’s temporary identity (TID) is generated by the user himself, which is inconvenient to be managed and can be easily forged. The reputation values of users also need to be considered. In this paper, an identity based signcryption scheme for VANETs is proposed. In the novel scheme, TID is generated by key generation center (KCG) and a personal reputation system is produced. The security analysis of the scheme shows that our scheme is practical. © Springer Nature Singapore Pte Ltd 2020.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A mutual authentication lightweight rfid protocol for iot devices 2nd

A mutual authentication lightweight rfid protocol for iot de...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Lu, Yong Wang, Anxi Liu, Shuai School of Management Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University GuiyangGuizhou550025 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou510632 China

ISBN: (纸本)9789811561122

The IoT data security is a hot topic at a data time. Personal privacy data may be easily leaked to data collectors in an open network environment. If the collectors get enough data, they can analyze the habit and interest of every IoT user, which may give helpful advice or cause endless harass. RFID authentication protocol in IoT is a powerful way to avoid the essential data leaked to data collectors. The previous protocols protect the security of RFID system. But they cannot guard the privacy of RFID system. The protocol we proposed achieves both the privacy and security. © Springer Nature Singapore Pte Ltd 2020.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Self-feedback LSTM regression model for real-time particle source apportionment

引用

Journal of Environmental Sciences 2022年第4期34卷 10-20页

作者： Wei Wang Weiman Xu Shuai Deng Yimeng Chai Ruoyu Ma Guoliang Shi Bo Xu Mei Li Yue Li Trusted AI System Laboratory College of Computer ScienceNankai UniversityTianjin 300350China KLMDASR Tianjin Key Laboratory of Network and Data Security TechnologyTianjin 300350China State Environmental Protection Key Laboratory of Urban Ambient Air Particulate Matter Pollution Prevention and Control College of Environmental Science and EngineeringNankai UniversityTianjin 300071China Institute of Mass Spectrometry and Atmospheric Environment Guangdong Provincial Engineering Research Center for on-line source apportionment system of air pollution Jinan UniversityGuangzhou 510632China Guangdong-Hongkong-Macao Joint Laboratory of Collaborative Innovation for Environmental Quality Guangzhou 510632China

Atmospheric particulate matter pollution has attracted much wider attention *** recent years,the development of atmospheric particle collection techniques has put forwards new demands on the real-time source apportionments *** demands are summarized,in this paper,as how to set up new restraints in apportionment and how to develop a non-linear regression model to process complicated circumstances,such as the existence of secondary source and similar *** this study,we firstly analyze the possible and potential restraints in single particle source apportionment,then propose a novel three-step self-feedback long short-term memory(SF-LSTM)network for approximating the source *** proposed deep learning neural network includes three modules,as generation,scoring and refining,and regeneration *** from the scoring modules,SF-LSTM implants four loss functions representing four restraints to be followed in the apportionment,meanwhile,the regeneration module calculates the source contribution in a non-linear *** results show that the model outperforms the conventional regression methods in the overall performance of the four evaluation indicators(residual sum of squares,stability,sparsity,negativity)for the ***,in short time-resolution analyzing,SF-LSTM provides better results under the restraint of stability.

关键词： Time series Regression Self-feedback LSTM network Particle source apportionment

来源：评论

学校读者我要写书评

暂无评论

DAMIA: Leveraging domain adaptation as a defense against membership inference attacks

arXiv

引用

arXiv 2020年

作者： Huang, Hongwei Luo, Weiqi Zeng, Guoqiang Weng, Jian Zhang, Yue Yang, Anjia College of Informatin Science and Technology College of Cyber security National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangdong Key Laboratory of Data Security and Privacy Preserving Jinan University Guangzhou510632 China

Deep Learning (DL) techniques allow one to train a model from a dataset, and the model can be adopted to solve tasks. DL has attracted much interest given its fancy performance and potential market value, while security issues are amongst the most colossal concerns. Being a core engine of DL, models may be prone to the membership inference attack, where an attacker determines whether a given sample is from the dataset the model trained on. Efforts have been made to hinder the attack but unfortunately, they may be subject to a major overhead or impaired usability. In this paper, we propose and implement DAMIA, leveraging Domain Adaptation (DA) as a defense to counter membership inference attacks. Our observation is that during the training process, DA obfuscates the dataset to be protected using another related dataset, and derives a model that underlyingly extracts the features from both the original dataset and the introduced dataset. Seeing that the model is obfuscated, membership inference fails, while the extracted common features provide supports for usability. Extensive experiments have been conducted, which validates our intuition. The model counters the membership inference attacks and has a negligible footprint to the usability. Our experiment also excludes a few factors that may hinder the performance of DAMIA, providing a potential guideline that instructs the vendors and researchers to benefit from our solution in a timely manner. Copyright © 2020, The Authors. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Onionchain: Towards balancing privacy and traceability of blockchain-based applications

arXiv

引用

arXiv 2019年

作者： Zhang, Yue Weng, Jian Weng, Jiasi Li, Ming Luo, Weiqi College of Informatin Science and Technology College of Cyber security National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangdong Key Laboratory of Data Security and Privacy Preserving Jinan University Guangzhou510632 China

With the popularity of Blockchain comes grave security related concerns. Achieving privacy and traceability simultaneously remains an open question. Efforts have been made to address the issues, while they may subject to specific scenarios. This paper studies how to provide a more general solution for this open question. Concretely, we propose Onionchain, featuring a suite of protocols, offering both traceability and privacy. As the term implies, our Onionchain is inspired by Onion routing. We investigate the principles of Onion routing carefully and integrate its mechanism together with Blockchain technology. We advocate the Blockchain community to adopt Onionchain with the regards of privacy and traceability. To this end, a case-study of Onionchain, which runs in the context of Vehicular Ad Hoc Networks (VANETs), is proposed, providing the community a guideline to follow. Systematic security analysis and extensive experiments are also conducted to validate our secure and cost-effective Onionchain. Copyright © 2019, The Authors. All rights reserved.

关键词： Blockchain

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：