检索结果-内蒙古大学图书馆

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui 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 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 School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

An Exploratory Study on the Usage and Readability of Messages Within Assertion Methods of Test Cases

学校读者我要写书评

暂无评论

An Exploratory Study on the Usage and Readability of Message...

Natural Language-Based software engineering (NLBSE), IEEE/ACM International Workshop on

作者： Taryn Takebayashi Anthony Peruma Mohamed Wiem Mkaouer Christian D. Newman Information and Computer Sciences Department University of Hawai'i at Manoa Honolulu Hawai'i USA Department of Software Engineering Rochester Institute of Technology Rochester New York USA

Unit testing is a vital part of the software development process and involves developers writing code to verify or assert production code. Furthermore, to help comprehend the test case and troubleshoot issues, developers have the option to provide a message that explains the reason for the assertion failure. In this exploratory empirical study, we examine the characteristics of assertion messages contained in the test methods in 20 open-source Java systems. Our findings show that while developers rarely utilize the option of supplying a message, those who do, either compose it of only string literals, identifiers, or a combination of both types. Using standard English readability measuring techniques, we observe that a beginner's knowledge of English is required to understand messages containing only identifiers, while a 4th -grade education level is required to understand messages composed of string literals. We also discuss shortcomings with using such readability measuring techniques and common anti-patterns in assert message construction. We envision our results incorporated into code quality tools that appraise the understandability of assertion messages.

关键词：

Microservice Auto-Scaling Algorithm Based on Workload Prediction in Cloud-Edge Collaboration Environment

学校读者我要写书评

暂无评论

Microservice Auto-Scaling Algorithm Based on Workload Predic...

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Zijun Peng Bing Tang Wei Xu Qing Yang Ehsanullah Hussaini Yuqiang Xiao Haiyan Li School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China Center of Network and Education Technology Guangzhou Maritime University Guangzhou China

Cloud computing centrally consolidates hardware and computing resources, offering efficient and cost-effective services. However, as cloud computing centers are predominantly built and operated in a fully centralized fashion, the increased distance between these centers and users can lead to a decline in service quality. Real-time interaction and high business continuity are crucial in scenarios like traffic monitoring, AR/VR applications, and the Internet of Things (IoT). Edge computing is better suited to meet the demands of such latency-sensitive business needs. By analyzing and processing massive data directly at edge computing nodes, which focus on network edge devices, reliance on transmission resources is reduced, consequently improving the overall quality and performance of services. Nevertheless, resource-constrained edge nodes require efficient utilization of available infrastructure capacity to ensure specific service level objectives (SLO) for applications. Therefore, this paper introduces XScale, a cloud-edge collaborative system that enables microservices to adaptively scale elastically. XScale applies a Bi-LSTM with an attention mechanism to forecast the workload of microservices. When combined with mechanisms designed to handle burst traffic and a cloud-edge collaborative load forwarding strategy, it achieves both adaptive elastic scaling and proactive load forwarding. Experimental results, obtained using real-world microservice workloads, indicate that the XScale system can significantly reduce SLO violations by 88%, increase resource utilization by 15%, and decrease average response time by 21% when compared to existing advanced reactive scaling methods.

关键词：

Quantum-based Feature Selection for Multi-Classification Problem in Complex Systems with Edge Computing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Wenjie Chen, Junxiu Wang, Yuxiang Gao, Peipei Lei, Zhibin Ma, Xu 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 999077 Hong Kong School of Software Qufu Normal University Shandong273165 China

The complex systems with edge computing require a huge amount of multi-feature data to extract appropriate insights for their decision-making, so it is important to find a feasible feature selection method to improve the computational efficiency and save the resource consumption. In this paper, a quantum-based feature selection algorithm for the multi-classification problem, namely QReliefF, is proposed, which can effectively reduce the complexity of algorithm and improve its computational efficiency. First, all features of each sample are encoded into a quantum state by performing operations CMP and Ry, then the amplitude estimation is applied to calculate the similarity between any two quantum states (i.e., two samples). According to the similarities, the Grover-Long method is utilized to find the nearest k neighbor samples, and then the weight vector is updated. After a certain number of iterations through the above process, the desired features can be selected with regards to the final weight vector and the threshold τ. Compared with the classical ReliefF algorithm, our algorithm reduces the complexity of similarity calculation from O(MN) to O(M), the complexity of finding the nearest neighbor from O(M) to O(√M), and resource consumption from O(MN) to O(MlogN). Meanwhile, compared with the quantum Relief algorithm, our algorithm is superior in finding the nearest neighbor, reducing the complexity from O(M) to O(√M). Finally, in order to verify the feasibility of our algorithm, a simulation experiment based on Rigetti with a simple example is performed. © 2023, CC BY.

关键词： Feature Selection

Requirements Analysis and Management for Benefiting Openness

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Linaker, Johan Wnuk, Krzysztof Department of Computer Science Lund University Lund Sweden Department of Software Engineering Blekinge Institute of Technology Karlskrona Sweden

Requirements engineering has recently been greatly influenced by the way how firms use Open Source software (OSS) and software Ecosystems (SECOs) as a part of their product development and business models. This is further emphasized by the paradigm of Open Innovation, which highlights how firms should strive to use both internal and external resources to advance their internal innovation and technology capabilities. The evolution from market-driven requirements engineering and management processes, has reshaped the understanding of what a requirement is, and how it is documented and used. In this work, we suggest a model for analyzing and managing requirements that is designed in the context of OSS and SECOs, including the advances and challenges that it brings. The model clarifies how the main stages of requirements engineering and management processes can be adjusted to benefit from the openness that the new context offers. We believe that the model is a first step towards the inevitable adaptation of requirements engineering to an open and informal arena, where processes and collaboration are decentralized, transparency and governance are the key success factors. © 2022, CC BY.

关键词： Requirements engineering

Privacy Computing Meets Metaverse: Necessity, Taxonomy and Challenges

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Chuan Li, Yuecheng Wu, Zhenpeng Mai, Chengyuan Liu, Youming Hu, Yanming Zheng, Zibin Kang, Jiawen School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China School of Automation Guangdong University of Technology Guangzhou China

Metaverse, the core of the next-generation Internet, is a computer-generated holographic digital environment that simultaneously combines spatio-temporal, immersive, real-time, sustainable, interoperable, and data-sensitive characteristics. It cleverly blends the virtual and real worlds, allowing users to create, communicate, and transact in virtual form. With the rapid development of emerging technologies including augmented reality, virtual reality and blockchain, the metaverse system is becoming more and more sophisticated and widely used in various fields such as social, tourism, industry and economy. However, the high level of interaction with the real world also means a huge risk of privacy leakage both for individuals and enterprises, which has hindered the wide deployment of metaverse. Then, it is inevitable to apply privacy computing techniques in the framework of metaverse, which is a current research hotspot. In this paper, we conduct comprehensive research on the necessity, taxonomy and challenges when privacy computing meets metaverse. Specifically, we first introduce the underlying technologies and various applications of metaverse, on which we analyze the challenges of data usage in metaverse, especially data privacy. Next, we review and summarize state-of-the-art solutions based on federated learning, differential privacy, homomorphic encryption, and zero-knowledge proofs for different privacy problems in metaverse. Finally, we show the current security and privacy challenges in the development of metaverse and provide open directions for building a well-established privacy-preserving metaverse system. For easy access and reference, we integrate the related publications and their codes into a GitHub repository: https://***/6lyc/***. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

Re-Smote: A Novel Imbalanced Sampling Method Based on Smote with Radius Estimation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Huiyuan, Jiang Yiyang, Li Baoyu, Liu Keming, Mao Yuhai, Zhao Software College Northeastern University Shenyang China College of Computer Science and Engineering Northeastern University Shenyang China Shenyang Edge Computing Technology Innovation Center Shenyang China

Imbalance is a distinctive feature of many datasets, and how to make the dataset balanced become a hot topic in machine learning field. Synthetic Minority Oversampling Technique (SMOTE) is the classical method to solve this problem. Although there are many researches about SMOTE, there is still problem of synthetic sample singularity. In order to solve the issues of class imbalance and diversity of generated samples, this paper proposes a hybrid resampling method for binary imbalanced data sets, RE-SMOTE, which is designed based on the improvements of two oversampling methods PF-SMOTE and SMOTE-WENN. First, the minority class sample points are divided into safe minority and boundary minority as used in PF. The boundary minority samples are re-organized by linear interpolation with nearest majority class samples, and the safe minority samples are re-organized by circle range that take the initial safe minority samples as center and the distance from the nearest majority samples as radius. Second, the noise samples are further cleaned according to relative density with WENN. Relative density is computed by ratio between number of majority sample and minority sample among reverse k-nearest neighbor samples. To verify the effectiveness and robustness of the proposed model, we conducted a comprehensive experimental study on 40 datasets selected from real applications. The experimental results show the superiority of RE-SMOTE over other state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

Blocking Flow Shop Scheduling Based on a Multi-Group Collaborative Sparrow Search Algorithm

学校读者我要写书评

暂无评论

Blocking Flow Shop Scheduling Based on a Multi-Group Collabo...

Chinese Control and Decision Conference, CCDC

作者： Kai Ma Yafei Geng Kan Xu Shiliang Guo Jie Yang School of Electrical Engineering Yanshan University Hebei China Shanghai Development Center of Computer Software Technology Shanghai China

ISBN: (纸本)9781665478977

The blocking flow shop scheduling problem (BFSP) prevails widely in the process manufacturing industry. In this paper, a multi-group collaborative sparrow search algorithm (MGCSSA) is proposed for minimizing the makespan for BFSP. Firstly, a collaborative initialization strategy is designed to generate initialized populations with certain quality. Second, an elite solution set and a multi-group collaboration mechanism are introduced to improve the adequacy of the global search, and the producer and scrounger position update formulas are improved to increase the population diversity. Then, three neighborhood heuristics are used to locally strengthen individuals in the elite solution set that enhance the ability of the algorithm to jump out of the local optimum. Finally, the proposed algorithm is evaluated experimentally in test cases. The experimental data and comparative results show that the proposed MGCSSA has superior performance and is highly competitive in solving BFSP.

关键词： Manufacturing industries Job shop scheduling Heuristic algorithms Sociology Collaboration Benchmark testing Search problems

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Taicai Duan, Yue Li, Dong Qi, Lei Shi, Yinghuan Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University China Huawei Noah’s Ark Lab China School of Computer Science and Engineering Southeast University China

Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, current mainstream methods overlook the potential of utilizing a pool of unlabeled data to construct the latent space, while only concentrating on designing sophisticated models to leverage the labeled data. Despite their effective usage of labeled data, these methods often require extra network structures, additional procedure, resulting in computational inefficiency. To address this issue, we propose a novel method to effectively utilize unlabeled data with the guidance of labeled data. Specifically, we tailor the pseudo-labeling technique from semi-supervised learning to explicitly reveal the relative magnitudes of optimization objective values hidden within the unlabeled data. Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space. Furthermore, we treat the VAE encoder and the Gaussian Process (GP) in Bayesian optimization as a unified deep kernel learning process, allowing the direct utilization of labeled data, which we term as Gaussian Process guidance. This directly and effectively integrates the goal of improving GP accuracy into the VAE training, thereby guiding the construction of the latent space. The extensive experiments demonstrate that our proposed method outperforms existing VAE-BO algorithms in various optimization scenarios. Our code will be published at https://***/TaicaiChen/PG-LBO. Copyright © 2023, The Authors. All rights reserved.

关键词： Gaussian distribution