检索结果-内蒙古大学图书馆

Chiral Chaos Enhanced Sensing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ge, Yun-Qiu Wang, Zhe Zhao, Qian-Chuan Zhang, Jing Liu, Yu-Xi School of Integrated Circuits Tsinghua University Beijing100084 China Frontier Science Center for Quantum Information Beijing China Department of Automation Tsinghua University Beijing100084 China School of Automation Science and Engineering Xi’an Jiaotong University Xi’an710049 China MOE Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China

Chirality refers to the property that an object and its mirror image cannot overlap each other by spatial rotation and translation, and can be found in various research fields. We here propose chiral chaos and construct a chiral chaotic device via coupled whispering gallery mode resonators, where routes to chaos exhibit pronounced chirality for two opposite pumping directions. The mechanism responsible for this phenomenon is that time-reversal symmetry of the traveling-wave light fields is broken by the Rayleigh scatterers inserted in resonators. Combining with the Lyapunov exponents, we propose metrics to measure the symmetry and chirality between different chaotic dynamics. We find that such a chiral chaotic device can be applied to achieve sensing with high sensitivity, wide detectable range, and strong robustness to the phase and orientation randomness of weak signals. Our work presents a promising candidate for on-chip sensing and may have applications in quantum networks and chaotic communications. © 2024, CC BY.

关键词： Whispering gallery modes

Mitigating Propensity Bias of Large Language Models for Recommender Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Guixian Yuan, Guan Cheng, Debo Liu, Lin Li, Jiuyong Zhang, Shichao School of Computer Science and Technology Engineering Research Center of Mine Digitalisation Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou221116 China UniSA STEM University of South Australia Adelaide5095 Australia Guangxi Key Lab of Multisource Information Mining & Security Guangxi Normal University Guilin541004 China

The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analyses of items) generated by these models. However, aligning this side information with collaborative information from historical interactions poses significant challenges. The inherent biases within LLMs can skew recommendations, resulting in distorted and potentially unfair user experiences. On the other hand, propensity bias causes side information to be aligned in such a way that it often tends to represent all inputs in a low-dimensional subspace, leading to a phenomenon known as dimensional collapse, which severely restricts the recommender system's ability to capture user preferences and behaviours. To address these issues, we introduce a novel framework named Counterfactual LLM Recommendation (CLLMR). Specifically, we propose a spectrum-based side information encoder that implicitly embeds structural information from historical interactions into the side information representation, thereby circumventing the risk of dimension collapse. Furthermore, our CLLMR approach explores the causal relationships inherent in LLM-based recommender systems. By leveraging counterfactual inference, we counteract the biases introduced by LLMs. Extensive experiments demonstrate that our CLLMR approach consistently enhances the performance of various recommender models. © 2024, CC BY-NC-ND.

关键词： Graph neural networks

HF-Mid: A Hybrid Framework of network Intrusion Detection for Multi-type and Imbalanced Data

学校读者我要写书评

暂无评论

HF-Mid: A Hybrid Framework of Network Intrusion Detection fo...

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： Weidong Zhou Tianbo Wang Guotao Huang Xiaopeng Liang Chunhe Xia Xiaojian Li Beijing Key Lab. of Network Technology Beihang University Beijing China School of Cyber Science and Technology Beihang University Beijing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing Guangxi Normal University Guilin China College of Computer Science and Information Technology Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

The data-driven deep learning methods have brought significant progress and potential to intrusion detection. However, there are two thorny problems caused by the characteristics of intrusion data: "multi-type features" and "data imbalance". The former means that forcefully and improperly transforming intrusion features from distinct metric spaces can result in semantic loss and noise. The latter indicates that the intrusion data is imbalanced in quantity and quality due to its complex spatial distribution. We propose a Hybrid Framework for Multi-type and Imbalance Data (HF-Mid) to address the above two problems. Firstly, we divide the intrusion features into equivalent and non-equivalent groups, and then embed them sequentially using Supervised Paragraph Vector-Distributed Memory (SPV-DM), which excels at modeling co-occurrence relationships, and Deep Neural network (DNN), which is suitable for modeling non-linear relationships, thereby solving the "multitype features" problem. Secondly, we adopt a low-noise collective matrix factorization (CMF) model to fuse the two obtained features for dimensionality reduction. Finally, we employ a multiple classifier to detect intrusion. During the classifier training stage, we design a genetic algorithm-based proportional sampling method to select high-quality samples in each training batch. thus addressing the "data imbalance" problem. The experimental results demonstrate the proposed framework exhibits an overall improvement of 5.9% and 1.5% in terms of accuracy and false positive rate on average, respectively.

关键词： Training Privacy Fuses Noise Semantics Artificial neural networks Feature extraction

FedDLM: A Fine-Grained Assessment Scheme for Risk of Sensitive information Leakage in Federated Learning-based Android Malware Classifier

学校读者我要写书评

暂无评论

FedDLM: A Fine-Grained Assessment Scheme for Risk of Sensiti...

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： Changnan Jiang Chunhe Xia Chen Chen Huacheng Li Tianbo Wang Xiaojian Li Beijing Key Lab. of Network Technology Beihang University Beijing China Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University Guilin China School of Cyber Science and Technology Beihang University Beijing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China College of Computer Science and Information Technology Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

In the traditional centralized Android malware classification framework, privacy concerns arise as it requires collecting users’ app samples containing sensitive information directly. To address this problem, new classification frameworks based on Federated Learning (FL) have emerged for privacy preservation. However, research shows that these frameworks still face risks of indirect information leakage due to adversary inference. Unfortunately, existing research lacks an effective assessment of the extent and location of this leakage risk. To bridge the gap, we propose the FedDLM, which provides a fine-grained assessment of the risk of sensitive information leakage in an FL-based Android malware classifier. FedDLM estimates attackers’ theoretical maximum inference ability from the information theory perspective to gauge the degree of leakage risk in the classifier effectively. It precisely identifies critical positions in the shared gradient where the leakage risk exists by utilizing characteristics of class activation in classifiers. Through extensive experiments on the Androzoo dataset, FedDLM demonstrates its superior effectiveness and precision compared to baseline methods in evaluating the risk of sensitive information leakage. The evaluation results provide valuable insights into information leakage problems in classifiers and targeted privacy protection methods.

关键词： Meters Privacy Federated learning information leakage Malware security Risk management

Generative Physical AI in Vision: A Survey

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Daochang Zhang, Junyu Dinh, Anh-Dung Park, Eunbyung Zhang, Shichao Xu, Chang School of Physics Mathematics and Computing The University of Western Australia CrawleyWA6009 Australia School of Computer Science and Engineering Central South University Changsha410083 China School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia Department of Artificial Intelligence Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin541004 China

Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D/4D content. Traditionally, generative models primarily focus on visual fidelity while often neglecting the physical plausibility of generated content. This gap limits their effectiveness in applications requiring adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative AI evolves to increasingly integrate physical realism and dynamic simulation, its potential to function as a "world simulator" expands—enabling the modeling of interactions governed by physics and bridging the divide between virtual and physical realities. This survey systematically reviews this emerging field of physics-aware generative AI in computer vision, categorizing methods based on how they incorporate physical knowledge—either through explicit simulation or implicit learning. We analyze key paradigms, discuss evaluation protocols, and identify future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for vision. The reviewed papers are summarized at https://***/BestJunYu/Awesome-Physics-aware-Generation. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

Watermarking for out-of-distribution detection 22

学校读者我要写书评

暂无评论

Watermarking for out-of-distribution detection

Proceedings of the 36th International Conference on Neural information Processing Systems

作者： Qizhou Wang Feng Liu Yonggang Zhang Jing Zhang Chen Gong Tongliang Liu Bo Han Department of Computer Science Hong Kong Baptist University School of Mathematics and Statistics The University of Melbourne School of Computer Science The University of Sydney PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology TML Lab The University of Sydney

ISBN: (纸本)9781713871088

Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogramming property of deep models and thus may not fully unleash their intrinsic strength: without modifying parameters of a well-trained deep model, we can reprogram this model for a new purpose via data-level manipulation (e.g., adding a specific feature perturbation to the data). This property motivates us to reprogram a classification model to excel at OOD detection (a new task), and thus we propose a general methodology named watermarking in this paper. Specifically, we learn a unified pattern that is superimposed onto features of original data, and the model's detection capability is largely boosted after watermarking. Extensive experiments verify the effectiveness of watermarking, demonstrating the significance of the reprogramming property of deep models in OOD detection.

关键词：

Parallel Optimization of Computational Fluid Dynamics Application code_saturne Based on Next Generation Sunway Supercomputer

学校读者我要写书评

暂无评论

Parallel Optimization of Computational Fluid Dynamics Applic...

International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)

作者： Anjun Liu Yin Liao Xihao Xu YanYan Chen Hongjun Zhong Jianming Wu Bo Kong Alexander Raikov Meng Guo Jinan Key Laboratory of High Performance Industrial Software Jinan Institute of Supercomputing Technology Jinan China Jinan Supercomputing-Zhejiang Yuansuan Industrial Simulation System Joint Laboratory Zhejiang Yuansuan Technology Co. Ltd Hangzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan ) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

code_saturne is an open-source general large-scale computational fluid dynamics software independently developed by Electricite de France since 1997. Due to its high computing performance, code_saturne has been widely used in the nuclear industry, heavy fuel and biomass combustion, particle tracking and other computational fluid dynamics fields. In this work, we implemented code_saturne on the new generation Sunway supercomputer (SW26010pro) at the first time. By applying the data value-taking technology of double cache, combined with Sunway shared memory technology, we have adapted the data structure and Modular programming of code_saturne conducively to the new generation Sunway supercomputer (SW26010pro) and accelerated the software hotspots the software hotspots by 1–2 times. After optimizing and porting, this software has successfully served in the numerical simulation of the lateral flow of fuel assemblies in the nuclear industry.

关键词：

Hyper-class representation of data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Shichao Li, Jiaye Zhang, Wenzhen Qin, Yongsong The School of Computer Science and Engineering Central South University Changsha410083 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guangxi Guilin541004 China

Data representation is usually a natural form with their attribute values. On this basis, data processing is an attribute-centered calculation. However, there are three limitations in the attribute-centered calculation, saying, inflexible calculation, preference computation, and unsatisfactory output. To attempt the issues, a new data representation, named as hyper-classes representation, is proposed for improving recommendation. First, the cross entropy, KL divergence and JS divergence of features in data are defined. And then, the hyper-classes in data can be discovered with these three parameters. Finally, a kind of recommendation algorithm is used to evaluate the proposed hyper-class representation of data, and shows that the hyper-class representation is able to provide truly useful reference information for recommendation systems and makes recommendations much better than existing algorithms, i.e., this approach is efficient and promising. © 2022, CC BY-NC-ND.

关键词： Data handling

JAX-CNV:A Whole-genome Sequencing-based Algorithm for Copy Number Detection at Clinical Grade Level

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2022年第6期20卷 1197-1206页

作者： Wan-Ping Lee Qihui Zhu Xiaofei Yang Silvia Liu Eliza Cerveira Mallory Ryan Adam Mil-Homens Lauren Bellfy Kai Ye Charles Lee Chengsheng Zhang Precision Medicine Center The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China The Jackson Laboratory for Genomic Medicine FarmingtonCT 06032USA School of Cyber Science and Engineering Xi’an Jiaotong UniversityXi’an 710049China Department of Pathology and Laboratory Medicine Perelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPA 19104USA School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China Department of Life Sciences Ewha Womans UniversitySeoul 03760South Korea

We aimed to develop a whole-genome sequencing(WGS)-based copy number variant(CNV)calling algorithm with the potential of replacing chromosomal microarray assay(CMA)for clinical ***-CNV is thus developed for CNV detection from WGS *** performance of this CNV calling algorithm was evaluated in a blinded manner on 31 samples and compared to the 112 CNVs reported by clinically validated CMAs for these 31 *** result showed that JAX-CNV recalled 100%of these ***,JAX-CNV identified an average of 30 CNVs per individual,representing an approximately seven-fold increase compared to calls of clinically validated *** validation of 24 randomly selected CNVs showed one false positive,i.e.,a false discovery rate(FDR)of 4.17%.A robustness test on lowercoverage data revealed a 100%sensitivity for CNVs larger than 300 kb(the current threshold for College of American Pathologists)down to 10×*** CNVs larger than 50 kb,sensitivities were 100%for coverages deeper than 20×,97%for 15×,and 95%for 10×.We developed a WGS-based CNV pipeline,including this newly developed CNV caller JAX-CNV,and found it capable of detecting CMA-reported CNVs at a sensitivity of 100%with about a FDR of 4%.We propose that JAX-CNV could be further examined in a multi-institutional study to justify the transition of first-tier genetic testing from CMAs to ***-CNV is available at https://***/TheJacksonlaboratory/JAX-CNV.

关键词： Copy number variant Chromosomal microarray assay Whole-genome sequencing JAX-CNV Genetic testing