检索结果-内蒙古大学图书馆

International Communication Systems and Networks and Workshops, COMSNETS

作者： Arunava Chaudhuri Shubhi Shukla Sarani Bhattacharya Debdeep Mukhopadhyay Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Centre for Computational and Data Sciences Indian Institute of Technology Kharagpur Kharagpur India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

With the rapid advancement of machine learning (ML) models and their widespread application across various sectors such as intrusion detection, medical diagnosis, natural language processing, and autonomous driving, these technologies have achieved remarkable success. However, this progress has also raised significant concerns about ensuring the security of ML models and protecting both private training data and model outputs from getting exposed in a shared cloud environment. To address these challenges, researchers have proposed various methodologies to create privacy-preserving, secure, and trustworthy model execution environments to prevent adversarial attacks. This study provides a comprehensive review of Trusted Execution Environment (TEE) implementations across different hardware accelerators. It also offers an overview of modern techniques for preserving privacy and security in execution environments, while identifying critical research gaps that require attention. In essence, this survey is an important resource for researchers, providing insights into recent methodologies and guiding them to focus on pressing research challenges.

关键词： Surveys Deep learning Training Privacy data privacy Training data data models Stability analysis Security Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Estimation of Neurological Diseases and Age Using Brain MRI 4th

Estimation of Neurological Diseases and Age Using Brain MRI

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Ashokkumar, K. Dharshan, K. Ragupathi, T. Pritam, Anem Sagar, Amujuru Gnana Department of Computer Science Engineering Sathyabama Institute of Science and Technology Chennai India School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Data Science and Business systems School of Computing SRM Institute of Science and Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9789819736898

Leveraging D-NN trained on neuroimaging data, we can effectively estimate the chronological ages of normal persons;this projected brain age has potential as a biomarker for identifying age-related disorders. The suggested technique employs a CNN cascade network from DL and the Support Vector Machine (SVM) algorithm from ML (SVM). These techniques have been employed to train MRI scans of the brain, classifying them into regular (unaffected by illness), Alzheimer’s disorder (AD), and neurocognitive disability. That we also have the ability to determine ages thanks to the age classifications on the photos. The brain MRI collection is trained using CNN and SVM, on which the classifications and age estimate will be carried out. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Discrete Controller Synthesis: Semantics-Aware Stepwise Policy Design via LLM

Towards Efficient Discrete Controller Synthesis: Semantics-A...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Ishimizu, Yusei Li, Jialong Yamauchi, Takuto Chen, Sinan Cai, Jinyu Hirano, Takanori Tei, Kenji School of Computing Tokyo Institute of Technology Tokyo Japan Waseda University Department of Computer Science and Engineering Tokyo Japan Kobe University Center of Mathematical and Data Sciences Kobe Japan

ISBN: (纸本)9798331530839

Discrete Controller Synthesis (DCS) is an automated generation technique to generate controllers from environment models and requirements. The time and space complexities of DCS are critical because they directly govern the feasibility of using DCS for real-time generation of controllers to cope with environmental changes. Stepwise DCS is considered a promising approach to prevent the construction of ineffective state spaces in the subsequent analysis of the full controller by analyzing sub-controllers that meet part of the requirements at an early stage. However, constructing a stepwise policy is a challenge, as the current methods often require domain experts to manually build it by understanding and reasoning the semantics of each sub-environment model and sub-requirement. To reduce the effort of manual construction, this paper introduces a method that leverages large language models (LLMs) to automate the generation of stepwise policies by utilizing the LLM's ability to understand and reason about the semantics of state machines. The evaluation using GPT-4 on a drone control scenario demonstrates the effectiveness of our method, with an average reduction of 82.2% in states and 91.2% in transitions. © 2024 IEEE.

关键词： Control system synthesis

来源：评论

学校读者我要写书评

暂无评论

Performance Characterization of Containerized DNN Training and Inference on Edge Accelerators

Performance Characterization of Containerized DNN Training a...

引用

International Conference on High Performance Computing

作者： Prashanthi S.K. Vinayaka Hegde Keerthana Patchava Ankita Das Yogesh Simmhan Department of Computational and Data Sciences Indian Institute of Science Bangalore INDIA

Edge devices have typically been used for DNN in-ferencing. The increase in the compute power of accelerated edges is leading to their use in DNN training also. As privacy becomes a concern on multi-tenant edge devices, Docker containers provide a lightweight virtualization mechanism to sandbox models. But their overheads for edge devices are not yet explored. In this work, we study the impact of containerized DNN inference and training workloads on an NVIDIA AGX Orin edge device and contrast it against bare metal execution on running time, CPU, GPU and memory utilization, and energy consumption. Our analysis provides several interesting insights on these overheads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Residual Dilated Convolutional Learning for Detection of Large Vessel Occlusion in Ischemic Stroke Patients 1

Deep Residual Dilated Convolutional Learning for Detection o...

引用

1st IEEE International Conference on Artificial Intelligence for Medicine, Health and Care, AIMHC 2024

作者： Chatterjee, Rohan Pourhomayoun, Mohammad Sagar, Dikshant Kaur, Manveen Mohammadi, Farnaz Lim, Jung Soo Vaishya, Arpit Amini, Navid Department of Computer Science California State University Los Angeles Los AngelesCA United States Genentech Computational Sciences Genentech Inc. South San FransicoCA United States

ISBN: (纸本)9798350371987

Rapid identification of large vessel occlusions (LVOs) is crucial when treating and managing patients with acute ischemic strokes (AIS). This urgency is due to the fact that LVOs are associated with high rates of post-stroke dependence and mortality. Furthermore, precise and prompt detection of such occlusions can assist in minimizing long-term functional and psychological ramifications. The conventional method for LVO detection requires manual examination of Computed Tomography Angiography (CTA) brain images. However, treatment delays frequently occur due to the unavailability of skilled radiologists specialized for these cases. In this study, we introduce a Three-Dimensional Deep Residual Dilated Convolutional Neural Network (DRDCNet-3D) that can harness the capabilities of dilated convolutions to improve spatial resolution. This method allows for rapid and precise detection of LVOs directly from three-dimensional CTA brain scans. Utilizing the recently published IACTA-EST dataset, our designed model has exhibited remarkable performance, boasting an AUC-ROC of 0.91 and an F1-score of 0.90. Such performance represents an average improvement of over 20% compared to existing state-of-the-art 3D medical image analysis models available in open-source platforms. This notable enhancement underscores the model’s efficacy in diagnosing large vessel occlusions (LVOs). Our approach equips physicians with valuable insights for determining optimal treatment strategies in suspected AIS cases. Accordingly, timely interventions can be carried out, reducing the risk of permanent severe damage and benefiting patient outcomes. ©2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Scheduling of Concurrent DNN Training and Inferencing on Accelerated Edges

Towards Efficient Scheduling of Concurrent DNN Training and ...

引用

Cluster, Cloud and Internet Computing Workshops (CCGridW), IEEE/ACM International Symposium on

作者： Prashanthi S K Vinayaka Hegde Yogesh Simmhan Department of Computational and Data Sciences Indian Institute of Science Bangalore INDIA

Edge devices are typically used to perform low-latency DNN inferencing close to the data source. However, with accelerated edge devices and privacy-oriented paradigms like Federated Learning, we can increasingly use them for DNN training too. This can require both training and inference workloads to be run concurrently on an edge device, without compromising on the inference latency. Here, we explore such concurrent scheduling on edge devices, and provide initial results demonstrating the interaction of training and inferencing on latency and throughput.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting VPN Traffic in Real-Time with Active Probing 22

Detecting VPN Traffic in Real-Time with Active Probing

引用

22nd International Symposium on Network Computing and Applications, NCA 2024

作者： Tian, Yuan Cao, Zechun Huang, Shou-Hsuan Stephen Department of Computer Science University of Houston HoustonTX United States Dept of Computational Engineering and Mathematical Sciences Texas A&M University-San Antonio San AntonioTX United States

ISBN: (纸本)9798331510183

Malicious attackers often exploit anonymity networks like VPNs to conceal their identities. This paper introduces a novel real-time detection algorithm based on discrepancies in packet round-trip times (RTTs) and active probing of VPN servers. When a client accesses a target server via a VPN, two distinct RTTs emerge anchored on the target: target-VPN and target-VPN-client. The proposed detection algorithm determines whether one or two significantly different RTT clusters are present, with two clusters indicating the use of a VPN. The focus of this study is the detection of Secure Shell (SSH) connections through VPNs. While measuring the RTT between the target and the client is relatively straightforward due to the packet exchange of the TCP/SSH protocol, estimating the RTT between the target and the VPN presents challenges. An active probing method is proposed to calculate the RTT, accounting for the potential involvement of a malicious or compromised VPN. By employing machine learning to analyze these RTTs, the system can effectively detect intruders utilizing VPNs. This research serves as a foundation for developing secure and efficient VPN detection systems, which are critical for preserving the integrity and privacy of digital resources. ©2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Feature Importance Identification for Time Series Classifiers

Feature Importance Identification for Time Series Classifier...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Meng, Han Wagner, Christian Triguero, Isaac Lab United Kingdom School of Computer Science Nottingham United Kingdom DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Department of Computer Science and Artificial Intelligence Granada Spain

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Time series classification is a challenging research area where machine learning techniques such as deep learning perform well, yet lack interpretability. Identifying the most important features for such classifiers provides a pathway to improving their interpretability. Several Feature Importance (FI) identification methods remove the contributions of features, i.e. observations at certain time steps of, from the input and evaluate the change in the classification result to measure the importance of features. As time series features cannot simply be deleted, current techniques generally rely on replacing features with constant or random values. While effective, this approach risks unexpected results in the classification and thus feature importance estimation-as the replacements used may be different to what the classifier encountered in the training phase. This is referred to as the Out-Of-Distribution problem. The OOD problem has been recognised in image and language models but have not received much attention in the context of time series classification. This work addresses the OOD problem in FI identification for time series classifiers. Specifically, we propose a method based on Conditional Variational Autoencoder to generate possible sets of within-distribution inputs, which are used to evaluate feature importance through marginalisation. Experiments on publicly accessible datasets are carried out showing that the method identifies the most important features with higher accuracy than existing methods, providing the basis for improved explainability of time series classifiers. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Elasticity and acoustic velocities of δ−AlOOH at extreme conditions: A methodology assessment

引用

Physical Review Materials 2024年第10期8卷 103601页

作者： Chenxing Luo (罗晨星) Yang Sun (孙阳) Renata M. Wentzcovitch Department of Applied Physics and Applied Mathematics Department of Physics Department of Earth and Environmental Sciences Lamont–Doherty Earth Observatory Data Science Institute Center for Computational Quantum Physics

Hydrous phases play a fundamental role in the deep-water cycle on Earth. Understanding their stability and thermoelastic properties is essential for constraining their abundance using seismic tomography. However, determining their elastic properties at extreme conditions is notoriously challenging. The challenges stem from the complex behavior of hydrogen bonds under high pressures and temperatures (P,Ts). In this study, we evaluate how advanced molecular dynamics simulation techniques can address these challenges by investigating the adiabatic elasticity and acoustic velocities of δ−AlOOH, a critical and prototypical high-pressure hydrous phase. We compared the performances of three methods to assess their viability and accuracy. The thermoelastic tensor was computed up to 140 GPa and temperatures up to 2700 K using molecular dynamics with a DeePMD machine-learning interatomic potential based on the SCAN meta-GGA functional. The excellent agreement with ambient condition single-crystal ultrasound measurements and the correct description of velocity changes induced by H-bond disorder-symmetrization transition observed at 10 GPa in Brillouin scattering measurements underscores the accuracy and efficacy of our approach.

关键词： Elasticity Geophysics High-pressure studies Hydrogen bonds Disordered systems Minerals Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

PartRePer-MPI: Combining Fault Tolerance and Performance for MPI Applications

arXiv

引用

arXiv 2023年

作者： Joshi, Sarthak Vadhiyar, Sathish Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

As we have entered Exascale computing, the faults in high-performance systems are expected to increase considerably. To compensate for a higher failure rate, the standard checkpoint/restart technique would need to create checkpoints at a much higher frequency resulting in an excessive amount of overhead which would not be sustainable for many scientific applications. Replication allows for fast recovery from failures by simply dropping the failed processes and using their replicas to continue the regular operation of the application. In this paper, we have implemented PartRePer-MPI, a novel fault-tolerant MPI library that adopts partial replication of some of the launched MPI processes in order to provide resilience from failures. The novelty of our work is that it combines both fault tolerance, due to the use of the User Level Failure Mitigation (ULFM) framework in the Open MPI library, and high performance, due to the use of communication protocols in the native MPI library that is generally fine-tuned for specific HPC platforms. We have implemented efficient and parallel communication strategies with computational and replica processes, and our library can seamlessly provide fault tolerance support to an existing MPI application. Our experiments using seven NAS Parallel Benchmarks and two scientific applications show that the failure-free overheads in PartRePer-MPI when compared to the baseline MVAPICH2, are only up to 6.4% for the NAS parallel benchmarks and up to 9.7% for the scientific applications. © 2023, CC BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：