检索结果-内蒙古大学图书馆

IEEE Symposium on Security and Privacy

作者： Peizhuo Lv Hualong Ma Kai Chen Jiachen Zhou Shengzhi Zhang Ruigang Liang Shenchen Zhu Pan Li Yingjun Zhang Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Department of Computer Science Metropolitan College Boston University USA Institute of Software Chinese Academy of Sciences China

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied. However, most of such watermarks fail upon model extraction attack, which utilizes input samples to query the target model and obtains the corresponding outputs, thus training a substitute model using such input-output pairs. In this paper, we propose a novel watermark to protect IP of DNN models against model extraction, named MEA-Defender. In particular, we obtain the watermark by combining two samples from two source classes in the input domain and design a watermark loss function that makes the output domain of the watermark within that of the main task samples. Since both the input domain and the output domain of our watermark are indispensable parts of those of the main task samples, the watermark will be extracted into the stolen model along with the main task during model extraction. We conduct extensive experiments on four model extraction attacks, using five datasets and six models trained based on supervised learning and self-supervised learning algorithms. The experimental results demonstrate that MEA-Defender is highly robust against different model extraction attacks, and various watermark removal/detection approaches.

关键词： Training Symbiosis Computational modeling Supervised learning Watermarking Artificial neural networks Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Achieving Lightweight Image Steganalysis with Content-Adaptive in Spatial Domain 11th

Achieving Lightweight Image Steganalysis with Content-Adapti...

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Chen, Junfu Fu, Zhangjie Sun, Xingming Li, Enlu Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9783030873547

Steganography is a technology that modifies complex regions of digital images to embed secret messages for the purpose of covert communication, while steganalysis is to detect whether secret messages are hidden in a digital image or not. However, the emergence of content-adaptive steganography such as S-UNIWARD prioritizes the embedding of secret messages in areas of textural complexity of images by embedding probability map guidelines. Such ways dramatically improve the security of steganography and impede the process of image steganalysis. Most of the existing steganalysis studies are aimed at improving the network structure to enhance the detection performance of the model, without considering the generation of embedding probability maps which can guide the training of the network model, eliminate some unnecessary distractions, shorten the training time and improve the final detection accuracy simultaneously. Therefore, how to obtain embedded probability maps and use them effectively becomes an important challenge in the field of steganalysis. In this paper, to solve the above problem we propose a content-adaptive lightweight network to implement an embedded probability map combined with steganalysis. Our steganalysis model includes two parts: embedding probability maps generation module and features processing module, which is trained Separately. The generation module adopts the basic framework and modifies the model to make it more suitable for steganography. In the features processing module, we adopt a pseudo-siamese architecture to manipulate two different input images. Next, we use the attention mechanism to assign weights to channel parameters. Finally, We use a simple data augmentation method to enhance our training dataset and improve final performance. Because our proposed model incorporates embedded probability maps as guidelines, experiments show that our proposed CNet has faster convergence speed, higher detection accuracy, and better robustness comp

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Interpretability Research of Variational Autoencoder Generation Process Based on Feature Disentanglement

Interpretability Research of Variational Autoencoder Generat...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Sicheng Xi Yanhui Peng Chongqing Key Laboratory of Computational Intelligence College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Computational Intelligence School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

Variational Autoencoder (VAE), as one of the main generative models, has a powerful representation learning capability. However, the hidden space representation learned by VAE is a high-dimensional and complex vector space, which makes it difficult to explain how the model gradually learns and composes the final generated results on different semantic features. To address this problem, firstly, this paper increases the degree of decoupling between different semantic features by increasing the independence between the hidden variables of the modal hermitian space, and explains the learning process of the model on different hermitian spaces by visualization based on the feature decoupling model. In addition, this paper also proposes a hidden variable contribution index to measure the influence of different dimensional hidden variables on the generation results, so as to explain the learning process of the model.

关键词： Training Seminars Representation learning Visualization Correlation Semantics Vectors

来源：评论

学校读者我要写书评

暂无评论

How to Route CUBIC and BBR Packets in Space

How to Route CUBIC and BBR Packets in Space

引用

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Shuo Huang Zhiyuan Wang Wenhao Lu Kai Shen Jiayi Zhang Shan Zhang Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China State Key Laboratory of Software Development Environment Beijing China

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

Low-earth-orbit satellite constellation (e.g., Starlink) is becoming the indispensable component of future Internet. Due to the mobility nature, ground-satellite links (GSLs) and inter-satellite links (ISLs) are not as stable as the fiber links of wired Internet. Consequently, end-to-end TCP connections traversing the LEO constellation will suffer from packet loss and latency variation caused by GSL handover and ISL failure. However, typical congestion control algorithms (e.g., loss-based CUBIC and bandwidth-estimated BBR) rely on these feedbacks to detect congestion in wired Internet. This leads to performance degradation for CUBIC/BBR in LEO satellite networks. In this paper, we propose a Default-and-Backup Routing (DB-R) mechanism to enhance the performance of CUBIC/BBR in LEO satellite networks. Specifically, DB-R leverages default routing to address the packet loss caused by frequent GSL handover. Moreover, DB- R utilizes backup routing to eliminate the packet loss caused by occasional ISL failure. Overall, DB-R only incurs negligible control overhead, but can effectively improve the performance of CUBIC and BBR in LEO satellite networks. We implement DB-R in Linux kernel and evaluate its performance based on OpenSN (i.e., an open-source libarary for emulating LEO satellite networks). Results show that our DB-R mechanism can improve the average throughput of CUBIC (and BBR, respectively) by up to 37 % (and 18 %, respectively) compared with classic OSPF.

关键词： Satellites Linux Wireless networks Low earth orbit satellites Packet loss Handover Routing Throughput Internet Kernel

来源：评论

学校读者我要写书评

暂无评论

Explainable Machine Learning for High Frequency Trading Dynamics Discovery

SSRN

引用

SSRN 2023年

作者： Han, Henry Forrest, Jeffrey Yi-Lin Wang, Jiacun Yuan, Shuining Fei, Han Li, Diane Department of Computer Science School of Engineering and Computer Science Baylor University WacoTX76798 United States Department of Accounting Economics and Finance Slippery Rock University Slippery RockPA16057 United States Department of Computer Science and Software Engineering Monmouth University West Long Branch NJ07764 United States Quantitative Finance The Gabelli School of Business Fordham University New YorkNY10023 United States College of Computer science Jiangsu University Jiangsu Zhenjiang212013 China School of Business and Technology

High-frequency trading (HFT) plays an essential role in the financial market. However, how to discover and reveal trading dynamics remains a challenge in Fintech. In this study, we propose a novel explainable machine learning approach: Feature-Interpolation-based Dimension Reduction SCAN (FIDRSCAN) to handle the challenge by creating a trading map. The trading map deciphers an HFT security’s trading dynamics by marking the status of each transaction, grouping transactions in clusters, and identifying the trading markers. The proposed method presents new feature interpolation techniques to build a more informative and explainable feature space to unveil hidden trading behaviors. It mines HFT data in their low-dimensional embedding to seek exceptional trading markers and classify the statuses of transactions. We validate the meaningfulness and effectiveness of the trading markers discovered from FIDR-SCAN in trading besides examining its special characteristics. Besides, we apply the proposed algorithm to cryptocurrency data and achieve reliable performance. To the best of our knowledge, this study is the first to use interpretable machine learning to reveal HFT trading dynamics. © 2023, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Automated Test Case Repair Using Language Models

arXiv

引用

arXiv 2024年

作者： Yaraghi, Ahmadreza Saboor Holden, Darren Kahani, Nafiseh Briand, Lionel School of Electrical Engineering and Computer Science University of Ottawa OttawaONK1N 5N6 Canada Lero The Research Ireland Centre for Software University of Limerick Ireland Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Ensuring the quality of software systems through testing is essential, yet maintaining test cases poses significant challenges and costs. The need for frequent updates to align with the evolving system under test often entails high complexity and cost for maintaining these test cases. Further, unrepaired broken test cases can degrade test suite quality and disrupt the software development process, wasting developers’ time. To address this challenge, we present TARGET (TEST REPAIR GENERATOR), a novel approach leveraging pre-trained code language models for automated test case repair. TARGET treats test repair as a language translation task, employing a two-step process to fine-tune a language model based on essential context data characterizing the test breakage. To evaluate our approach, we introduce TARBENCH, a comprehensive benchmark we developed covering 45,373 broken test repairs across 59 open-source projects. Our results demonstrate TARGET’s effectiveness, achieving a 66.1% exact match accuracy. Furthermore, our study examines the effectiveness of TARGET across different test repair scenarios. We provide a practical guide to predict situations where the generated test repairs might be less reliable. We also explore whether project-specific data is always necessary for fine-tuning and if our approach can be effective on new projects. © 2024, CC BY.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Gradient-Guided Test Case Generation for Image Classification software

Gradient-Guided Test Case Generation for Image Classificatio...

引用

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： Shunhui Ji Yunhe Li Hai Dong Mingxuan Xiao Pengcheng Zhang Mengyuan Zhang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The widespread use of deep neural networks (DNNs) in image classification sofwares underlines the importance of the robustness. Researchers have proposed sparse adversarial attack methods for generating test cases, which add pixel-level perturbations to construct the test case to mislead the target model. However, the existing methods have certain limitations, such as high time cost, poor flexibility, and poor quality of the test cases. To address these issues, we propose a gradient-guided test case generation method (GGTM) to evaluate the robustness of image classification software. The method firstly identifies the key region in the image based on the gradient-weighted class activation mapping (Grad-CAM) and the prediction confidence of the target model on the input image. In the key region, it selects a set of pixels as candidate perturbation pixels according to the gradient value and the change of loss function. Then perturbations are added to the candidate perturbation pixels after applying a random dropout strategy to reduce some candidate perturbation pixels which is used to avoid local optimum. For the initially constructed test case which can mislead the target model, after removing redundant and unimportant perturbations, perturbations are re-added to optimize the test case. Experiments show the effectiveness of GGTM, which achieves 100% attack success rate. And the test cases generated by GGTM have the best perturbation sparsity. Furthermore, compared with the baseline method SparseAG which achieves optimal perturbation sparsity among the baseline methods, GGTM significantly improves the efficiency.

关键词： Costs Perturbation methods Artificial neural networks Predictive models software Robustness Image classification

来源：评论

学校读者我要写书评

暂无评论

Performance of OTFS-NOMA Scheme for Coordinated Direct and Relay Transmission Networks in High-Mobility Scenarios

arXiv

引用

arXiv 2023年

作者： Xu, Yao Du, Zhen Yuan, Weijie Jia, Shaobo Leung, Victor C.M. School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China The School of Information Engineering Zhengzhou University Zhengzhou450001 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Department of Electrical and Computer Engineering The University of British Columbia VancouverBCV6T 1Z4 Canada

In this paper, an orthogonal time frequency space (OTFS) based non-orthogonal multiple access (NOMA) scheme is investigated for the coordinated direct and relay transmission system, where a source directly communicates with a near user with high mobile speed, and it needs the relaying assistance to serve the far user also having high mobility. Due to the coexistence of signal superposition coding and multi-domain transformation, the performance of OTFS-based NOMA is usually challenging to be measured from a theoretical perspective. To accurately evaluate the system performance of the proposed scheme, we derive the closed-form expressions for the outage probability and the outage sum rate by using the Inversion formula and characteristic function. Numerical results verify the performance superiority and the effectiveness of the proposed scheme. 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

A unitary weights based one-iteration quantum perceptron algorithm for non-ideal training sets

arXiv

引用

arXiv 2023年

作者： Liu, Wenjie Gao, PeiPei Wang, Yuxiang Yu, Wenbin Zhang, Maojun Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China College of Computer Science and Information Technology Guangxi Normal University Guilin China

In order to solve the problem of non-ideal training sets (i.e., the less-complete or over-complete sets) and implement one-iteration learning, a novel efficient quantum perceptron algorithm based on unitary weights is proposed, where the singular value decomposition of the total weight matrix from the training set is calculated to make the weight matrix to be unitary. The example validation of quantum gates {H, S, T, CNOT, Toffoli, Fredkin} shows that our algorithm can accurately implement arbitrary quantum gates within one iteration. The performance comparison between our algorithm and other quantum perceptron algorithms demonstrates the advantages of our algorithm in terms of applicability, accuracy, and availability. For further validating the applicability of our algorithm, a quantum composite gate which consists of several basic quantum gates is also illustrated. © 2023, CC BY.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Audio Steganography Based Backdoor Attack for Speech Recognition software

Audio Steganography Based Backdoor Attack for Speech Recogni...

引用

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： Mengyuan Zhang Shunhui Ji Hanbo Cai Hai Dong Pengcheng Zhang Yunhe Li Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

With the growing prevalence of deep learning in the speech area, speech recognition, voice control, and related applications have become integral parts of people's lives. However, the rise of malicious third-party platforms has introduced significant security concerns, particularly through backdoor attacks. These attacks implant triggers that manipulate speech recognition models to produce specific labels, thereby compromising the system's integrity. Studying speech backdoor attacks is crucial for evaluating the security of speech recognition software, and iden-tifying and addressing potential vulnerabilities. Existing methods for speech backdoor attacks usually employ fixed perturbations as triggers. However, these perturbations may be discernible to the human ear, making them easily detectable. To address this issue, we propose a frequency domain-embedded backdoor attack method based on echo hiding. Echo hiding is a steganography technique based on audio. This method embeds hidden information into the frequency spectrum of the echo signal, leveraging the masking property of the human auditory system. It is difficult to arouse suspicion or detect the presence of hidden information since echo is perceived as a natural phenomenon in auditory perception. Furthermore, it does not cause a significant decrease in audio quality. Experimental results show the effectiveness of our method in different settings.

关键词： Training Steganography Perturbation methods Frequency-domain analysis Speech recognition Ear Implants

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：