Information Sciences最新文献_第5页

TPFL: Privacy-preserving personalized federated learning mitigates model poisoning attacks

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-27 DOI: 10.1016/j.ins.2025.121901

Shaojun Zuo , Yong Xie , Hehua Yao , Zhijie Ke

{"title":"TPFL: Privacy-preserving personalized federated learning mitigates model poisoning attacks","authors":"Shaojun Zuo , Yong Xie , Hehua Yao , Zhijie Ke","doi":"10.1016/j.ins.2025.121901","DOIUrl":"10.1016/j.ins.2025.121901","url":null,"abstract":"<div><div>Privacy-Preserving Federated Learning (PPFL) has become an emerging machine learning paradigm in recent years. However, PPFL is more difficult to detect model poisoning attacks because of its encrypted data, and the server cannot accurately identify them due to the crafted encrypted malicious local gradients uploaded by the adversaries. Most of the previous PPFL work is based on calculating the distance or correlation between local gradients to identify suspicious local gradients. In a setting with a high degree of non-IID, such schemes cannot effectively detect malicious gradients, as non-IID data can cause the distance between gradients to be far or the correlation to be weak, thereby affecting detection accuracy. In order to solve this problem, this paper designs a personalized global model defense scheme TPFL based on two trapdoors public-key cryptosystem, which can resist the encryption model poisoning without violating the PPFL privacy guarantee, and alleviate the problem of model training performance degradation caused by non-IID data. We evaluate the performance on two benchmark datasets (MNIST and CIFAR10), and the results show that TPFL can effectively resist two typical model poisoning attacks. At the same time, in the case of no attacks, the convergence of our model is similar to that of the baseline FL algorithm FedAvg, indicating that TPFL also has fidelity.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"702 ","pages":"Article 121901"},"PeriodicalIF":8.1,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143156645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exponential anti-synchronization in the mean squared sense for space-time discrete fuzzy stochastic complex networks with uncertainties

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-27 DOI: 10.1016/j.ins.2025.121898

Zhouhong Li , Xiaofang Meng , Yu Fei , Jinde Cao , Mahmoud Abdel-Aty

{"title":"Exponential anti-synchronization in the mean squared sense for space-time discrete fuzzy stochastic complex networks with uncertainties","authors":"Zhouhong Li , Xiaofang Meng , Yu Fei , Jinde Cao , Mahmoud Abdel-Aty","doi":"10.1016/j.ins.2025.121898","DOIUrl":"10.1016/j.ins.2025.121898","url":null,"abstract":"<div><div>This article presents a discussion of the mean squared exponential anti-synchronization of discrete-time and space stochastic fuzzy complex networks (DTS-SFCNs) that are subject to uncertainties. This paper addresses the issue of anti-synchronisation in discrete complex networks in terms of both time and space. Consequently, it differs from existing publications on discrete-time complex networks or continuous-time complex networks with reaction-diffusions. Besides, in contrast with the boundary controller presented in the preceding report on complex networks, this report proposes a feedback controller for DTS-SFCNs. The theory of statistics, the method of Lyapunov-Krasovskii functionals (LKF), and the technique of linear matrix inequalities (LMIs) are applied to derive criteria for the mean square exponential anti-synchronization (MSEAS) of the aforementioned DTS-SFCNs under the condition of zero boundary constraints. Subsequently, the results for uncertain DTS-SFCNs are investigated using the approach of matrix decompositions and the Schur complement lemma, taking into account the disturbances of uncertain dynamics. This study demonstrates that the uncertain network is capable of achieving exponential anti-synchronization in the mean squared sense when selected parameters include a large interval length of the space variable, a small diffusive intensity, and uncertain coefficients. To demonstrate the feasibility of this approach, a numerical example is provided herewith.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"702 ","pages":"Article 121898"},"PeriodicalIF":8.1,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143156647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced decision-making for urban climate change transportation policies using q-rung orthopair fuzzy rough fairly information aggregation

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-27 DOI: 10.1016/j.ins.2025.121900

Hafiz Muhammad Athar Farid , Muhammad Riaz , Patrick Siarry , Vladimir Simic

{"title":"Enhanced decision-making for urban climate change transportation policies using q-rung orthopair fuzzy rough fairly information aggregation","authors":"Hafiz Muhammad Athar Farid , Muhammad Riaz , Patrick Siarry , Vladimir Simic","doi":"10.1016/j.ins.2025.121900","DOIUrl":"10.1016/j.ins.2025.121900","url":null,"abstract":"<div><div>Formulating and implementing effective transportation policies is of the utmost importance in the context of increasingly imperative urban climate change issues. Utilizing q-rung orthopair fuzzy rough fairly aggregation operators, this paper presents an innovative method for enhancing decision-making in urban transportation policy development. These operators provide a dynamic multi-attribute decision making (MADM) framework particularly for urban climate and transportation problems that are complex, ambiguous, and comprise multiple criteria. By incorporating “q-rung orthopair fuzzy rough sets” (q-ROFRSs) and fairly operations, this methodology provides a comprehensive and systematic method for evaluating and prioritizing sustainable transportation policies while taking into account the inherent ambiguity and imprecision in urban climate change data. This study makes a significant contribution to the field of urban climate change policy development by providing a novel decision-support instrument that improves the transparency, fairness, and efficacy of decision-making process. The findings highlight the significance of incorporating rough set techniques in addressing the complexities of urban climate change transportation policy development, ultimately leading to more resilient and sustainable urban environments.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"702 ","pages":"Article 121900"},"PeriodicalIF":8.1,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143100210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Laws of large numbers for Sugeno integrals

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-13 DOI: 10.1016/j.ins.2024.121813

Pedro Terán

引用次数: 0

Prescribed-time nonsingular sliding mode control based on neural network for trajectory tracking of nonlinear systems

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-10 DOI: 10.1016/j.ins.2024.121850

Chao Jia , Xiaohua Liu , Fanlin Jia , Xiao He

{"title":"Prescribed-time nonsingular sliding mode control based on neural network for trajectory tracking of nonlinear systems","authors":"Chao Jia , Xiaohua Liu , Fanlin Jia , Xiao He","doi":"10.1016/j.ins.2024.121850","DOIUrl":"10.1016/j.ins.2024.121850","url":null,"abstract":"<div><div>Considering the influence of external time-varying disturbances on trajectory tracking control of nonlinear systems, a novel prescribed-time nonsingular sliding mode control (SMC) is proposed. Firstly, based on the definition of prescribed time stability, a lemma of practical prescribed time stability is proposed, which guarantees the system states converge to a region within the prescribed time. Secondly, a prescribed time SMC method is designed, which does not contain negative power terms in the controller and solves the singular problem. In addition, a continuous function is adopted instead of the sign function to reduce chattering, and it is also considered in the stability proof. The stability analysis shows that whatever it is in the sliding stage or the reaching stage, the tracking error is prescribed time stable. On the basis of prescribed time SMC method, the neural network (NN) is introduced to approximate the unknown model information. Finally, compared with other existing control methods, the results of simulation demonstrate that the proposed method exhibits superior performance, encompassing the achievement of prescribed time stability, the elimination of chattering, and the capability to analyze unknown model information via neural networks.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"701 ","pages":"Article 121850"},"PeriodicalIF":8.1,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A data-morphology-based counterfactual generation method for trustworthy artificial intelligence

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-08 DOI: 10.1016/j.ins.2024.121844

José Daniel Pascual-Triana , Alberto Fernández , Javier Del Ser , Francisco Herrera

{"title":"Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A data-morphology-based counterfactual generation method for trustworthy artificial intelligence","authors":"José Daniel Pascual-Triana , Alberto Fernández , Javier Del Ser , Francisco Herrera","doi":"10.1016/j.ins.2024.121844","DOIUrl":"10.1016/j.ins.2024.121844","url":null,"abstract":"<div><div>Explainable Artificial Intelligence (XAI) is a pivotal research domain aimed at clarifying AI systems, particularly those considered “black boxes” due to their complex, opaque nature. XAI seeks to make these AI systems more understandable and trustworthy, providing insight into their decision-making processes. By producing clear and comprehensible explanations, XAI enables users, practitioners, and stakeholders to trust a model's decisions. This work analyses the value of data morphology strategies in generating counterfactual explanations. It introduces the Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF) method, a model-agnostic counterfactual generator that leverages data morphology to estimate a model's decision boundaries. The ONB-MACF method constructs hyperspheres in the data space whose covered points share a class, mapping the decision boundary. Counterfactuals are then generated by incrementally adjusting an instance's attributes towards the nearest alternate-class hypersphere, crossing the decision boundary with minimal modifications. By design, the ONB-MACF method generates feasible and sparse counterfactuals that follow the data distribution. Our comprehensive benchmark from a double perspective (quantitative and qualitative) shows that the ONB-MACF method outperforms existing state-of-the-art counterfactual generation methods across multiple quality metrics on diverse tabular datasets. This supports our hypothesis, showcasing the potential of data-morphology-based explainability strategies for trustworthy AI.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"701 ","pages":"Article 121844"},"PeriodicalIF":8.1,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inception MLP: A vision MLP backbone for multi-scale feature extraction

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-08 DOI: 10.1016/j.ins.2024.121865

Jia Li , Rongchao Yang , Xinyan Cao , Bo Zeng , Zhandong Shi , Wei Ren , Xixin Cao

{"title":"Inception MLP: A vision MLP backbone for multi-scale feature extraction","authors":"Jia Li , Rongchao Yang , Xinyan Cao , Bo Zeng , Zhandong Shi , Wei Ren , Xixin Cao","doi":"10.1016/j.ins.2024.121865","DOIUrl":"10.1016/j.ins.2024.121865","url":null,"abstract":"<div><div>Recently, MLP-based networks have demonstrated remarkable performance in computer vision with simple but efficient structures. However, most existing MLP architectures struggle to balance the modeling of local and global regional information and often rely on static token mixing matrices for information fusion, disregarding the distinctiveness of different input contents. In this study, we propose inception MLP (iMLP), which employs multiple cross-MLP branches with varying receptive field sizes to simultaneously capture short-range and long-range dependencies. Meanwhile, the channel partition ratio <em>γ</em> is dynamically adjusted to better align with model characteristics as the network deepens. In addition, considering the diversity of input contents, we incorporate a lightweight, content-adaptive module to enable dynamic and efficient feature fusion. Experimental results demonstrate the versatility of iMLP as a competitive vision backbone across various visual tasks. For instance, our iMLP-S achieves 82.1% top-1 accuracy on the ImageNet-1K classification benchmark with only 20M parameters and extremely high throughput, outperforming state-of-the-art MLP-based models with a better trade-off between accuracy and computational efficiency.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"701 ","pages":"Article 121865"},"PeriodicalIF":8.1,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Three-way concept lattice construction and association rule acquisition

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-08 DOI: 10.1016/j.ins.2024.121867

Junping Xie , Jing Yang , Jinhai Li , Mingwei He , Huaxiang Song

引用次数: 0

Boosting occluded person re-identification by leveraging occlusion attributes

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-08 DOI: 10.1016/j.ins.2024.121866

Tengfei Ren , Qiusheng Lian , Jiale Chen

{"title":"Boosting occluded person re-identification by leveraging occlusion attributes","authors":"Tengfei Ren , Qiusheng Lian , Jiale Chen","doi":"10.1016/j.ins.2024.121866","DOIUrl":"10.1016/j.ins.2024.121866","url":null,"abstract":"<div><div>Occluded person re-identification (ReID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Currently, occlusion augmentation-based methods have not fully exploited the occlusion attributes, resulting in suboptimal results. We introduce a novel ReID framework, dubbed Occlusion Attributes boosted Occluded Person Re-Identification (OA-ReID), aimed at leveraging the occlusion attributes for pedestrian-focused feature learning. Firstly, we propose an occlusion emulator (OE) that generates artificially occluded images towards emulating the occlusion scenarios. Both the original image and the corresponding artificially occluded image are jointly used for model training. Secondly, we present two crucial components, namely the inductive hard (IH) sample mining and the Occlusion-Informed Part Transformer (OIPT). The IH sample mining leverages the obstacle category to construct inductive triplets, which induces the model to extract identity-relevant features. The OIPT integrates the obstacle position information into our ReID framework to rectify the erroneous attention on occlusions, promoting reliable target pedestrian localization. Through extensive experiments, we show OA-ReID achieves state-of-the-art performance on both occluded and holistic person ReID benchmarks.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"701 ","pages":"Article 121866"},"PeriodicalIF":8.1,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive fault compensation for global performance tracking control of sensor faulty MIMO nonlinear systems with unmeasured states

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-01-07 DOI: 10.1016/j.ins.2024.121862

Liuliu Zhang, Lingchen Zhu, Cheng Qian, Changchun Hua

{"title":"Adaptive fault compensation for global performance tracking control of sensor faulty MIMO nonlinear systems with unmeasured states","authors":"Liuliu Zhang, Lingchen Zhu, Cheng Qian, Changchun Hua","doi":"10.1016/j.ins.2024.121862","DOIUrl":"10.1016/j.ins.2024.121862","url":null,"abstract":"<div><div>In this article, the problem of global prescribed performance tracking control for multi-input multi-output (MIMO) nonlinear systems with sensor faults and unmeasured states is investigated. By constructing a state observer that incorporates an adaptive sensor fault compensation mechanism, the impact of the loss of sensor effectiveness is alleviated through the cubic absolute-value Lyapunov function analysis method. Based on several transformation functions and a time-varying scaling function, the tracking errors are restricted within the global prescribed performance without the constrained initial conditions. Considering the abrupt change in tracking errors due to the existence of sensor faults, a monitoring function to supervise the excessive loss of sensor effectiveness is designed. Furthermore, a novel reconfigurable controller can be constructed with the detected fault time instant and the global prescribed performance. The analysis demonstrates that all signals remain bounded and the tracking errors are maintained within the designed global prescribed performance regardless of sensor faults. Finally, the efficacy of the presented control scheme is demonstrated by the simulation results.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"700 ","pages":"Article 121862"},"PeriodicalIF":8.1,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143150774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0