Mobile apps are prevalent in everyone's daily life. However, apps are oftentimes defective, undermining their convenience, and therefore automated testing and analysis of apps are developed to enhance apps' qu...
详细信息
In this paper we propose a mobile-agent-based web service composition (MAWSC) model for the dynamic web service composition (WSC). As compared with the traditional WSC models, our model avoids bottleneck of data trans...
详细信息
In the dynamic field of deep learning, accurately estimating model performance while ensuring data privacy against diverse and unlabeled test datasets presents a critical challenge. This is primarily due to the signif...
ISBN:
(纸本)9781939133441
In the dynamic field of deep learning, accurately estimating model performance while ensuring data privacy against diverse and unlabeled test datasets presents a critical challenge. This is primarily due to the significant distributional shifts between training and test datasets, which complicates model evaluation. Traditional methods for assessing model accuracy often require direct access to the entire test dataset, posing significant risks of data leakage and model theft. To address these issues, we propose a novel approach: Distribution-Aware Adversarial Perturbation (DAAP). This method is designed to estimate the accuracy of deep learning models on unlabeled test datasets without compromising privacy. Specifically, DAAP leverages a publicly available dataset as an intermediary to bridge the gap between the model and the test data, effectively circumventing direct interaction and mitigating privacy concerns. By strategically applying adversarial perturbations, DAAP minimizes the distributional discrepancies between datasets, enabling precise estimation of model performance on unseen test data. We present two specialized strategies for white-box and black-box model contexts: the former focuses on reducing output entropy disparities, while the latter manipulates distribution discriminators. Overall, the DAAP introduces a novel framework for privacy-preserving accuracy estimation in model evaluation. This novel approach not only addresses critical challenges related to data privacy and distributional shifts but also enhances the reliability and integrity of model performance assessments. Our extensive evaluation on the CIFAR-10-C, CIFAR-100-C, and CelebA datasets demonstrates the effectiveness of DAAP in accurately estimating performance while safeguarding both data and model privacy.
The low-altitude economy (LAE), driven by unmanned aerial vehicles (UAVs) and other aircraft, has revolutionized fields such as transportation, agriculture, and environmental monitoring. In the upcoming six-generation...
详细信息
This paper introduces a non-Horn rule WRM which is a weak form of rational monotony. We explore the effects of adding this non-Horn rule to the rules for the preferential inference. In this paper, a relation |~ is sai...
详细信息
This paper introduces a non-Horn rule WRM which is a weak form of rational monotony. We explore the effects of adding this non-Horn rule to the rules for the preferential inference. In this paper, a relation |~ is said to be P + WRM iff it is a preferential inference and satisfies the rule WRM. We establish the representation theorem for P + WRM, and compare the strength of WRM with some non-Horn rules appearing in literatures. Moreover, we explore the relation between P + WRM and conditional logic, and demonstrate that P + WRM is equivalent to 'flat' fragment of conditional logic CS4.2. Another contribution of this paper is to explore the relation between two special kinds of preferential models, i.e., PRC model and quasi-linear model. Main result reveals that the latter is a special form of the former.
Fast changing knowledge on the Internet can be acquired more efficiently with the help of automatic document summarization and updating techniques. This paper describes a novel approach for multi-document update summa...
详细信息
Fast changing knowledge on the Internet can be acquired more efficiently with the help of automatic document summarization and updating techniques. This paper describes a novel approach for multi-document update summarization. The best summary is defined to be the one which has the minimum information distance to the entire document set. The best update summary has the minimum conditional information distance to a document cluster given that a prior document cluster has already been read. Experiments on the DUC/TAC 2007 to 2009 datasets (http://***/, http://***/tac/) have proved that our method closely correlates with the human summaries and outperforms other programs such as LexRank in many categories under the ROUGE evaluation criterion.
To improve the performance of K-means clustering algorithm, this paper presents a new hybrid approach of Enhanced artificial bee colony algorithm and Kmeans(EABCK). In EABCK, the original artificial bee colony algorit...
详细信息
To improve the performance of K-means clustering algorithm, this paper presents a new hybrid approach of Enhanced artificial bee colony algorithm and Kmeans(EABCK). In EABCK, the original artificial bee colony algorithm(called ABC) is enhanced by a new mutation operation and guided by the global best solution(called EABC). Then, the best solution is updated by Kmeans in each iteration for data clustering. In the experiments, a set of benchmark functions was used to evaluate the performance of EABC with other comparative ABC variants. To evaluate the performance of EABCK on data clustering, eleven benchmark datasets were utilized. The experimental results show that EABC and EABCK outperform other comparative ABC variants and data clustering algorithms, respectively.
Public blockchain has outstanding performance in transaction privacy protection because of its anonymity. The data openness brings feasibility to transaction behavior analysis. At present, the transaction data of the ...
详细信息
Public blockchain has outstanding performance in transaction privacy protection because of its anonymity. The data openness brings feasibility to transaction behavior analysis. At present, the transaction data of the public chain are huge, including complex trading objects and relationships. It is difficult to extract attributes and predict transaction behavior by traditional methods. To solve the problems, we extract the transaction features to construct the Ethereum transaction heterogeneous information network (HIN), and propose graph-neural-network-based transaction prediction method for public blockchain in HINs, which can divide the network into subgraphs according to connectivity and make the prediction results of transaction behavior more accurate. Experiments show that the execution time consumption of the proposed transaction subgraph division method is reduced by 70.61% on average compared with the search method. The accuracy of the proposed behavior prediction method also improve compared with the traditional random walk method, with an average accuracy of 83.82%.
The Bitcoin network comprises numerous nodes, necessitating users to invest significant network requests and time in comprehending its network topology. In this paper, we propose a Bitcoin network topology discovery a...
详细信息
The Bitcoin network comprises numerous nodes, necessitating users to invest significant network requests and time in comprehending its network topology. In this paper, we propose a Bitcoin network topology discovery algorithm that utilizes lightweight probe nodes to facilitate rapid transmission of network protocols. Building upon this, we introduce a node layer clustering algorithm based on filtering stable network nodes, enabling parallel discovery of the network topology. Additionally, we present an adaptive method for dynamically displaying the layered structure of the network topology. Experimental results demonstrate that our proposed method reduces communication overhead by approximately 72.16% when achieving a 95% similarity in network topology. Furthermore, the algorithm is applicable for discovering the network topology in other blockchain networks with similar structures.
Natural phenomena of collective intelligence(CI) occurring in physical space show a potential approach to effective large-scale human collaboration in cyberspace. Based on existing explanatory understanding of CI, thi...
Natural phenomena of collective intelligence(CI) occurring in physical space show a potential approach to effective large-scale human collaboration in cyberspace. Based on existing explanatory understanding of CI, this perspective proposes a constructive model for building artificial CI systems, i.e., problem-oriented CI phenomena with AI-powered information integration and feedback.
暂无评论