NSTL国家科技图书文献中心

1. Robustness of multilayer interdependent higher-order network NSTL国家科技图书文献中心

Peng H. | Zhao Y.... - 《Journal of network and computer applications》 - 2025,233(Jan.) - 1.1～1.14 - 共14页

摘要： study the robustness* of MIHN by investigating the* | stable robustness* compared to the other three* | failure rate and weakest robustness* due to its ring* | © 2024 Elsevier LtdIn real-world complex | systems, most networks are interconnected with other

关键词： Multilayer interdependent higher-order network | Percolation theory | Robustness

2. AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation NSTL国家科技图书文献中心

Li, Lin | Qiu, Jianing ... - 《International Journal of Computer Vision》 - 2025,133(2) - 929～950 - 共22页

摘要： robustness substantially. Recently, data augmentation (DA | automated DA method specific for robustness. A novel | adversarial robustness. This allows our method to | regarding both accuracy and robustness. It can also be | robustness. Code and pre-trained models are available at

关键词： Adversarial robustness | Adversarial training | Data augmentation | Automated data augmentation

3. Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models NSTL国家科技图书文献中心

HAIPENG WANG | ZHENGYUAN WEI ... - 《ACM transactions on software engineering and methodology》 - 2025,34(1) - 8.1～8.68 - 共68页

摘要： enhancing the robustness* property of deep learning (DL* | ) models, many state-of-the-art robustness-oriented | model robustness. The experiments show that Clover | % and 48%100% in terms of robustness* improvement ratio* | In the testing-retraining pipeline for

关键词： context-awareness | fuzzing algorithm | robustness | assessment | metric

4. Evaluating the adversarial robustness of Arabic spam classifiers NSTL国家科技图书文献中心

Anwar,Alajmi | Imtiaz,Ahmad ... - 《Neural computing & applications》 - 2025,37(6) - 4323～4343 - 共21页

摘要： to deceive NLP models. Adversarial robustness | contributions exist in the field of NLP adversarial robustness | robustness of an Arabic NLP model, especially in a classic | Several studies have exposed the vulnerability | of Natural Language Processing (NLP) models to

关键词： Arabic natural language processing | Adversarial attacks | Robustness | Arabic spam classification

5. Enhancing the global and local robustness of networks: A network motif-based approach NSTL国家科技图书文献中心

Yang S. | Xiao R. - 《Communications in nonlinear science and numerical simulation》 - 2025,140(Jan. Pt.2) - 1.1～1.16 - 共16页

摘要： global network properties (global robustness) and* local* | . Therefore, optimizing network robustness* to maintain* | . With the deepening of network robustness* research* | robustness of networks is related to network motifs | . Considering the optimization of the robustness* based on the*

关键词： Edge rewiring | Global robustness | Local robustness | Motif-based

6. Solving the robustness puzzle: The joint impact of optimization approach, robustness metrics, and scenarios on water resources management under deep uncertainty NSTL国家科技图书文献中心

Jiajia Huang | Matteo Sangiorgio ... - 《Journal of Environmental Management》 - 2025,373(Jan.) - 123540.1～123540.13 - 共13页

摘要： system robustness* and performance is investigated* | robustness and performance when scenarios represent a wide | identifying robust solutions using different robustness | The concept of robustness* has been widely used* | robustness remains challenging due to the existence of

关键词： Water resources management | Uncertainty | Robustness | Optimization | Climate change adaptation

7. Meta Recommendation With Robustness Improvement NSTL国家科技图书文献中心

Zeyu Zhang | Chaozhuo Li ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(2) - 781～793 - 共13页

摘要： alleviating this problem, in this paper, we propose a robust | simultaneously, we design a novel distributionally robust* model* | Meta learning has been recognized as an | effective remedy for solving the cold-start problem in the | recommendation domain. Existing models aim to learn how to

关键词： Training | Testing | Metalearning | Robustness | Films | Tuning | Recommender systems | Mathematical models | Convergence | Upper bound

8. Improving Robustness in IoT Malware Detection through Execution Order Analysis NSTL国家科技图书文献中心

GAO-YU LIN | PO-YUAN WANG ... - 《ACM Transactions on Embedded Computing Systems》 - 2025,24(1) - 4～ - 共17页

摘要： the robustness* of these models is of paramount* | methods to rigorously test our model's robustness* by* | The rapid expansion of the Internet of Things | (IoT) has significantly increased the prevalence of | malware targeting IoT devices. Although machine learning

关键词： Execution order | Malware detector | Machine learning | Deep learning | Detector robustness

9. On the Robustness of Object Detection Models on Aerial Images NSTL国家科技图书文献中心

Haodong He | Jian Ding ... - 《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1～12 - 共12页

摘要：The robustness* of object detection models is a* | . While numerous studies have explored the robustness* of* | robustness of object detection models on aerial images | robustness of mainstream object detection models and | robustness of models. Furthermore, increasing the capacity

关键词： Object detection | Robustness | Benchmark testing | Clouds | Data models | Accuracy | Transformers | Feature extraction | Detectors | Visualization

10. Enhancing Federated Learning Robustness Using Locally Benignity-Assessable Bayesian Dropout NSTL国家科技图书文献中心

Jingjing Xue | Sheng Sun ... - 《IEEE transactions on information forensics and security》 - 2025,20 - 2464～2479 - 共16页

摘要： assessment, failing to maintain robustness* and convergence* | . Theoretical analysis proves the robustness* and convergence* | indicators and guarantee global robustness* over non-IID* | local robust* training based on fine-grained benignity* | client-side robust* training with Bayesian*

关键词： Bayes methods | Training | Servers | Data models | Robustness | Distributed databases | Uplink | Convergence | Computational modeling | Recurrent neural networks

摘要： study the robustness of MIHN by investigating the | stable robustness compared to the other three | failure rate and weakest robustness due to its ring | © 2024 Elsevier LtdIn real-world complex | systems, most networks are interconnected with other

关键词： Multilayer interdependent higher-order network | Percolation theory | Robustness

摘要： robustness substantially. Recently, data augmentation (DA | automated DA method specific for robustness. A novel | adversarial robustness. This allows our method to | regarding both accuracy and robustness. It can also be | robustness. Code and pre-trained models are available at

关键词： Adversarial robustness | Adversarial training | Data augmentation | Automated data augmentation

摘要： enhancing the robustness property of deep learning (DL | ) models, many state-of-the-art robustness-oriented | model robustness. The experiments show that Clover | % and 48%100% in terms of robustness improvement ratio | In the testing-retraining pipeline for

关键词： context-awareness | fuzzing algorithm | robustness | assessment | metric

摘要： to deceive NLP models. Adversarial robustness | contributions exist in the field of NLP adversarial robustness | robustness of an Arabic NLP model, especially in a classic | Several studies have exposed the vulnerability | of Natural Language Processing (NLP) models to

关键词： Arabic natural language processing | Adversarial attacks | Robustness | Arabic spam classification

摘要： global network properties (global robustness) and local | . Therefore, optimizing network robustness to maintain | . With the deepening of network robustness research | robustness of networks is related to network motifs | . Considering the optimization of the robustness based on the

关键词： Edge rewiring | Global robustness | Local robustness | Motif-based

摘要： system robustness and performance is investigated | robustness and performance when scenarios represent a wide | identifying robust solutions using different robustness | The concept of robustness has been widely used | robustness remains challenging due to the existence of

关键词： Water resources management | Uncertainty | Robustness | Optimization | Climate change adaptation

关键词： Training | Testing | Metalearning | Robustness | Films | Tuning | Recommender systems | Mathematical models | Convergence | Upper bound

摘要： the robustness of these models is of paramount | methods to rigorously test our model's robustness by | The rapid expansion of the Internet of Things | (IoT) has significantly increased the prevalence of | malware targeting IoT devices. Although machine learning

关键词： Execution order | Malware detector | Machine learning | Deep learning | Detector robustness

摘要：The robustness of object detection models is a | . While numerous studies have explored the robustness of | robustness of object detection models on aerial images | robustness of mainstream object detection models and | robustness of models. Furthermore, increasing the capacity

关键词： Object detection | Robustness | Benchmark testing | Clouds | Data models | Accuracy | Transformers | Feature extraction | Detectors | Visualization

摘要： assessment, failing to maintain robustness and convergence | . Theoretical analysis proves the robustness and convergence | indicators and guarantee global robustness over non-IID | local robust training based on fine-grained benignity | client-side robust training with Bayesian

关键词： Bayes methods | Training | Servers | Data models | Robustness | Distributed databases | Uplink | Convergence | Computational modeling | Recurrent neural networks

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： study the robustness* of MIHN by investigating the* | stable robustness* compared to the other three* | failure rate and weakest robustness* due to its ring* | © 2024 Elsevier LtdIn real-world complex | systems, most networks are interconnected with other

摘要： enhancing the robustness* property of deep learning (DL* | ) models, many state-of-the-art robustness-oriented | model robustness. The experiments show that Clover | % and 48%100% in terms of robustness* improvement ratio* | In the testing-retraining pipeline for

摘要： system robustness* and performance is investigated* | robustness and performance when scenarios represent a wide | identifying robust solutions using different robustness | The concept of robustness* has been widely used* | robustness remains challenging due to the existence of

摘要： the robustness* of these models is of paramount* | methods to rigorously test our model's robustness* by* | The rapid expansion of the Internet of Things | (IoT) has significantly increased the prevalence of | malware targeting IoT devices. Although machine learning

摘要：The robustness* of object detection models is a* | . While numerous studies have explored the robustness* of* | robustness of object detection models on aerial images | robustness of mainstream object detection models and | robustness of models. Furthermore, increasing the capacity

摘要： assessment, failing to maintain robustness* and convergence* | . Theoretical analysis proves the robustness* and convergence* | indicators and guarantee global robustness* over non-IID* | local robust* training based on fine-grained benignity* | client-side robust* training with Bayesian*