检索结果-内蒙古大学图书馆

Mixed-Precision Computing in the GRIST Dynamical Core for Weather and Climate Modelling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Siyuan Zhang, Yi Wang, Yiming Liu, Zhuang Li, Xiaohan Xue, Wei 2035 Future Laboratory PIESAT Information Technology Co. Ltd. Beijing China Ministry of Education Key Laboratory for Earth System Modelling Department of Earth System Science Tsinghua University Beijing China Chinese Academy of Meteorological Sciences Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Beijing Research Institute Nanjing University of Information Science and Technology Beijing China

Atmosphere modelling applications become increasingly memory-bound due to the inconsistent development rates between processor speeds and memory bandwidth. In this study, we mitigate memory bottlenecks and reduce the computational load of the GRIST dynamical core by adopting the mixed-precision computing strategy. Guided by a limited-degree of iterative development principle, we identify the equation terms that are precision insensitive and modify them from double- to single-precision. The results show that most precision-sensitive terms are predominantly linked to pressure-gradient and gravity terms, while most precision-insensitive terms are advective terms. The computational cost is reduced without compromising the solver accuracy. The runtime of the model’s hydrostatic solver, non-hydrostatic solver, and tracer transport solver is reduced by 24%, 27%, and 44%, respectively. A series of idealized tests, real-world weather and climate modelling tests, has been performed to assess the optimized model performance qualitatively and quantitatively. In particular, in the high-resolution weather forecast simulation, the model sensitivity to the precision level is mainly dominated by the small-scale features. While in long-term climate simulation, the precision-induced sensitivity can form at the large scale. Copyright © 2024, The Authors. All rights reserved.

关键词： Weather forecasting

Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polyps

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Manan, Malik Abdul Jinchao, Feng Yaqub, Muhammad Ahmed, Shahzad Imran, Syed Muhammad Ali Chuhan, Imran Shabir Khan, Haroon Ahmed Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of computer science and information technology Superior University Lahore Pakistan Interdisciplinary Research Institute Faculty of Science Beijing University of Technology Beijing China Islamabad Pakistan

Colorectal polyps are structural abnormalities of the gastrointestinal tract that can potentially become cancerous in some cases. The study introduces a novel framework for colorectal polyp segmentation named the Multi-Scale and Multi-Path Cascaded Convolution Network (MMCC-Net), aimed at addressing the limitations of existing models, such as inadequate spatial dependence representation and the absence of multi-level feature integration during the decoding stage by integrating multi-scale and multi-path cascaded convolutional techniques and enhances feature aggregation through dual attention modules, skip connections, and a feature enhancer. MMCC-Net achieves superior performance in identifying polyp areas at the pixel level. The Proposed MMCC-Net was tested across six public datasets and compared against eight SOTA models to demonstrate its efficiency in polyp segmentation. The MMCC-Net's performance shows Dice scores with confidence interval ranging between 77.43 ± 0.12, (77.08, 77.56) and 94.45 ± 0.12, (94.19, 94.71) and Mean Intersection over Union (MIoU) scores with confidence interval ranging from 72.71 ± 0.19, (72.20, 73.00) to 90.16 ± 0.16, (89.69, 90.53) on the six databases. These results highlight the model's potential as a powerful tool for accurate and efficient polyp segmentation, contributing to early detection and prevention strategies in colorectal cancer. © 2024, CC BY.

关键词： Semantic Segmentation

MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization

学校读者我要写书评

暂无评论

MEAT: Median-Ensemble Adversarial Training for Improving Rob...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhaozhe Hu Jia-Li Yin Bin Chen Luojun Lin Bo-Hao Chen Ximeng Liu Fujian Province Key Laboratory of Information Security and Network Systems Fuzhou China College of Computer Science and Big Data Fuzhou University Fuzhou China Department of Computer Science and Engineering Yuan Ze University Taiwan

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT.

关键词：

Meta-ZSDETR: Zero-shot DETR with Meta-learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Lu Zhang, Chenbo Zhao, Jiajia Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory China Department of Computer Science & Technology Tongji University China

Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we present the first method that combines DETR and meta-learning to perform zero-shot object detection, named Meta-ZSDETR, where model training is formalized as an individual episode based meta-learning task. Different from Faster R-CNN based methods that firstly generate class-agnostic proposals, and then classify them with visual-semantic alignment module, Meta-ZSDETR directly predict class-specific boxes with class-specific queries and further filter them with the predicted accuracy from classification head. The model is optimized with meta-contrastive learning, which contains a regression head to generate the coordinates of class-specific boxes, a classification head to predict the accuracy of generated boxes, and a contrastive head that utilizes the proposed contrastive-reconstruction loss to further separate different classes in visual space. We conduct extensive experiments on two benchmark datasets MS COCO and PASCAL VOC. Experimental results show that our method outperforms the existing ZSD methods by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

Meet-in-the-Middle Statistical Fault Analysis of the PRESENT lightweight Cryptosystem

学校读者我要写书评

暂无评论

Meet-in-the-Middle Statistical Fault Analysis of the PRESENT...

作者： Li, Wei Zhu, Xiao-Ming Gu, Da-Wu Li, Jia-Yao Cai, Tian-Pei School of Computer Science and Technology Donghua University Shanghai201620 China Department of Computer and Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Key Laboratory of Scalable Computing and System Shanghai200240 China Shanghai Key Laboratory of Integrate Administration Technologies for Information Security Shanghai200240 China

The lightweight block cipher PRESENT was presented at the International Conference on Cryptographic Hardware and Embedded systems (CHES) in 2007, and it has become a standard of ISO/IEC-29192-2 for lightweight cryptosystems since 2012. Within the environment of the Internet of Things, this cipher is applicable to Radio Frequency Identification, network sensors, and smart cards. Its secret key can be either 80 or 128 bits long, while the block is 128 bits long. Since the publication of the PRESENT, numerous forms of cryptanalysis have been developed in order to evaluate its level of security. Some examples of these attacks include the differential attack, the linear attack, the integral attack, the algebraic attack, the fault attack, the side-cube attack, and the Biclique attack. All of these cryptanalyses are on the basis of the assumption that an attack using a chosen plaintext or an attack using a known plaintext would occur. In order to carry out a chosen-plaintext attack, an attacker must have the ciphertexts along with the plaintexts that go along with them, whereas a known-plaintext attack requires a significant quantity of plaintexts and ciphertexts. The ciphertext-only attack is distinct from the chosen-plaintext attack and the known-plaintext attack, which require the ciphertext only in order to be successful. In this sense, the ciphertext-only attack is relevant in a range of scenarios. There is no research that has been released yet regarding PRESENT'S resilience to the ciphertext-only attack. This study presents a novel meet-in-the-middle statistical fault analysis using the approach of statistical analysis and meet-in-the-middle attack of PRESENT. This analysis is able to decrypt the 80-bit and 128-bit secret keys of PRESENT with a series of new distinguishers that include the Pearson correlation coefficient-Hamming weight, the Kullback Leibler divergence- Hamming weight, and the Jaccard similarity coefficient-Hamming weight-maximum likelihood estimatio

关键词： Side channel attack

Meta-ZSDETR: Zero-shot DETR with Meta-learning

学校读者我要写书评

暂无评论

Meta-ZSDETR: Zero-shot DETR with Meta-learning

International Conference on computer Vision (ICCV)

作者： Lu Zhang Chenbo Zhang Jiajia Zhao Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory China Department of Computer Science & Technology Tongji University China

关键词：

Two-Sided Online Task Assignment Based on Worker Portraits in Mobile CrowdSensing

学校读者我要写书评

暂无评论

Two-Sided Online Task Assignment Based on Worker Portraits i...

International Conference on computer Supported Cooperative Work in Design

作者： Zhenyang Mao Peng Li Guangzhong Liao Lei Nie Haizhou Bao Qin Liu School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China School of Cyber Science and Engineering Wuhan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Task assignment is a challenging problem in mobile crowdsensing (MCS), especially since workers and tasks are online. Existing work does not consider the portrait of the workers when assigning tasks, which may result in workers being assigned to fields they are not familiar with, thus affecting the quality of task completion. In this paper, we focus on online scenarios and identify a more practical task assignment problem, a two-sided (workers and tasks) online task assignment problem based on worker portrait in MCS. We decompose this problem into two subproblems: the worker portrait analysis problem (WPA) and the two-sided online personalized assignment problem (TOPA). To solve the WPA problem, we propose a worker portrait analysis algorithm that uses the semi-supervised model to describe the worker portrait at a fine-grained level. Then, based on the worker portrait, we propose a two-sided online personalized assignment algorithm to solve the TOPA problem. The proposed algorithm guarantees a lower bound on the assignment results by analyzing the worker portrait data. Moreover, we prove the TOPA problem is NP-hard and demonstrate the competitive ratio can achieve ln(max(u i,j )+1). Finally, we conduct extensive experiments on two datasets, and the experimental results show that our method outperforms baseline algorithms.

关键词： Analytical models Crowdsensing Federated learning Task analysis Synthetic data

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai 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 Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology