NSTL国家科技图书文献中心

1. Microarchitectural Security of Firecracker VMM for Serverless Cloud Platforms NSTL国家科技图书文献中心

Zane Weissman | Thore Tiemann ... - 《Information Systems Security》 - International Conference on Information Systems Security - 2025, - 3～24 - 共22页

摘要：Firecracker is a virtual machine manager (VMM | ) purpose-built by AWS for serverless cloud platforms | - services that run code for thousands of end users on a | per-task basis, automatically managing server | infrastructure. In addition to architectural attacks, AWS

关键词： System security | Microarchitectural security | Virtual machines | Hypervisor | Serverless | Cloud systems

2. A Hypervisor Based Platform for the Development and Verification of Reliable Software Applications NSTL国家科技图书文献中心

N. Petrellis | M. Mavropoulos ... - 《Embedded Computer Systems: Architectures,Modeling,and Simulation,Part II》 - International Conference on Embedded Computer Systems - 2025, - 261～276 - 共16页

摘要： the hypervisor* configuration files that are* | In the XANDAR project, a holistic model-based | toolchain has been formulated that follows the X-by | -Construction (XbC) paradigm i.e., a "step-wise refinement | from specifications to executable code" that results

关键词： Code optimizations | HEFT scheduling | EDF scheduling | Hypervisor | Software components | Runnables

3. Analytical model of a virtualized computing system using semi-markov approach NSTL国家科技图书文献中心

R. K.,Bhardwaj | Lakhwinder,Sharma - 《Life Cycle Reliability and Safety Engineering》 - 2025,14(1) - 93～104 - 共12页

摘要： host before triggering virtual machine monitor | virtual computing system, potentially leading to system | migrate virtual* machines from operating host to backup* | Software aging can impact the efficiency of a | crashes or failures over time. A well-defined approach

关键词： Virtual machine monitor | Software aging | Software rejuvenation | Semi-Markov | Regenerative Process | Steady State Performance

4. Self-adjusting resilient control plane for virtual software-defined optical networks NSTL国家科技图书文献中心

Mogyorosi F. | Babarczi P.... - 《Optical Switching and Networking》 - 2025,55(Jan.) - 1.1～1.10 - 共10页

摘要： softwarization and virtualization, virtual* software-defined* | the placement to the dynamically changing virtual | hypervisor. In a resilient optical control plane each | hypervisor instance through short control paths, which | propose an intelligent greedy hypervisor* placement*

关键词： Machine learning | Resilient hypervisor placement | Self-adjusting algorithms | Virtual software-defined optical networks

5. Viewpoint Modeling with Multi-task Learning for Vehicle Re-identification NSTL国家科技图书文献中心

Baitong Cui | Shuai Li ... - 《PRICAI 2024,Part IV》 - Pacific Rim International Conference on Artificial Intelligence - 2025, - 37～49 - 共13页

摘要： Viewpoint Modeling with Multi-task learning (VMM) that | datasets, VeRI and VeRI-Wild, demonstrate that VMM | existing methods with similar network scales, VMM | Vehicle Re-Identification (V-ReID) is a | crucial research topic in the field of intelligent

关键词： Vehicle re-Identification | Representation learning | Multi-Task learning | Feature decoupling

6. Hardware-assisted virtualization extensions for LEON processors in mixed-criticality systems NSTL国家科技图书文献中心

Losa B. | Parra P.... - 《Microprocessors and microsystems》 - 2025,112(Feb.) - 1.1～1.17 - 共17页

摘要：, applications run on a separation kernel hypervisor, a | hypervisor, enhancing system performance. Our proposed | handled by the hypervisor* and which ones by the guest* | hypervisor intervention, matching the performance when non | © 2024 The AuthorsThe increasing complexity of

关键词： Full virtualization | Hardware assisted virtualization | LEON processor | On-board systems

7. A simple interface circuit for edge inference kernels based on SC-LNO memristor crossbar NSTL国家科技图书文献中心

Siqi Wang | Yinyu Liu ... - 《Microelectronics journal》 - 2025,156(Feb.) - 106537.1～106537.8 - 共8页

摘要： (VMM) operations can be achieved through the | the efficient realization of VMM* operations. The* | Edge inference chips based on non-volatile | memory hold promise in mitigating the bottleneck | attributed to substantial data movement in artificial

关键词： Memristor crossbar | Interface circuit | ASIC | SC-LNO memristor | TIA

8. Efficient Hybrid Training Method for Neuromorphic Hardware Using Analog Nonvolatile Memory NSTL国家科技图书文献中心

Dongseok Kwon | Sung Yun Woo ... - 《IEEE transactions on neural networks and learning systems》 - 2025,36(1) - 807～819 - 共13页

摘要：-scale vector-matrix multiplication (VMM) operations | Neuromorphic hardware using nonvolatile analog | synaptic devices provides promising advantages of | reducing energy and time consumption for performing large | . However, the reported training methods for neuromorphic

关键词： Hardware | Training | Neuromorphics | Tuning | Nonvolatile memory | Neural networks | Protocols

9. Toward Providing Root Privilege to Flagship HPC Users with Thin-Hypervisor NSTL国家科技图书文献中心

Takaaki Fukai | Manami Mori ... - 《2024 IEEE International Conference on Cluster Computing Workshops》 - IEEE International Conference on Cluster Computing Workshops - 2024, - 188～189 - 共2页

摘要： root privileges. Commodity virtual machine | potential of the thin hypervisor* technique on the flagship* | experimental result shows that our prototype hypervisor* has a* | HPC clusters do not currently provide root | priv-ileges on the operating system to users, however

关键词： Degradation | Virtual machine monitors | Conferences | Prototypes | Cluster computing | Kernel | Tuning

10. WeSee: Using Malicious #VC Interrupts to Break AMD SEV-SNP NSTL国家科技图书文献中心

Benedict Schlüter | Supraja Sridhara ... - 《2024 IEEE Symposium on Security and Privacy: SP 2024, San Francisco, California, USA, 20-23 May 2024, [v.1]》 - IEEE Symposium on Security and Privacy - 2024, - 4220～4238 - 共19页

摘要： hypervisor controlled by the cloud provider. AMD introduced | communication between the VM and the untrusted hypervisor. We | present WeSee attack, where the hypervisor* injects* | the VM and the hypervisor. WeSee shows that using | AMD SEV-SNP offers VM-level trusted execution

摘要：Firecracker is a virtual machine manager (VMM | ) purpose-built by AWS for serverless cloud platforms | - services that run code for thousands of end users on a | per-task basis, automatically managing server | infrastructure. In addition to architectural attacks, AWS

关键词： System security | Microarchitectural security | Virtual machines | Hypervisor | Serverless | Cloud systems

摘要： the hypervisor* configuration files that are* | In the XANDAR project, a holistic model-based | toolchain has been formulated that follows the X-by | -Construction (XbC) paradigm i.e., a "step-wise refinement | from specifications to executable code" that results

关键词： Code optimizations | HEFT scheduling | EDF scheduling | Hypervisor | Software components | Runnables

摘要： host before triggering virtual machine monitor | virtual computing system, potentially leading to system | migrate virtual* machines from operating host to backup* | Software aging can impact the efficiency of a | crashes or failures over time. A well-defined approach

关键词： Virtual machine monitor | Software aging | Software rejuvenation | Semi-Markov | Regenerative Process | Steady State Performance

摘要： softwarization and virtualization, virtual* software-defined* | the placement to the dynamically changing virtual | hypervisor. In a resilient optical control plane each | hypervisor instance through short control paths, which | propose an intelligent greedy hypervisor* placement*

关键词： Machine learning | Resilient hypervisor placement | Self-adjusting algorithms | Virtual software-defined optical networks

摘要： Viewpoint Modeling with Multi-task learning (VMM) that | datasets, VeRI and VeRI-Wild, demonstrate that VMM | existing methods with similar network scales, VMM | Vehicle Re-Identification (V-ReID) is a | crucial research topic in the field of intelligent

关键词： Vehicle re-Identification | Representation learning | Multi-Task learning | Feature decoupling

摘要：, applications run on a separation kernel hypervisor, a | hypervisor, enhancing system performance. Our proposed | handled by the hypervisor* and which ones by the guest* | hypervisor intervention, matching the performance when non | © 2024 The AuthorsThe increasing complexity of

关键词： Full virtualization | Hardware assisted virtualization | LEON processor | On-board systems

摘要： (VMM) operations can be achieved through the | the efficient realization of VMM* operations. The* | Edge inference chips based on non-volatile | memory hold promise in mitigating the bottleneck | attributed to substantial data movement in artificial

关键词： Memristor crossbar | Interface circuit | ASIC | SC-LNO memristor | TIA

摘要：-scale vector-matrix multiplication (VMM) operations | Neuromorphic hardware using nonvolatile analog | synaptic devices provides promising advantages of | reducing energy and time consumption for performing large | . However, the reported training methods for neuromorphic

关键词： Hardware | Training | Neuromorphics | Tuning | Nonvolatile memory | Neural networks | Protocols

摘要： root privileges. Commodity virtual machine | potential of the thin hypervisor* technique on the flagship* | experimental result shows that our prototype hypervisor* has a* | HPC clusters do not currently provide root | priv-ileges on the operating system to users, however

关键词： Degradation | Virtual machine monitors | Conferences | Prototypes | Cluster computing | Kernel | Tuning

摘要： hypervisor controlled by the cloud provider. AMD introduced | communication between the VM and the untrusted hypervisor. We | present WeSee attack, where the hypervisor* injects* | the VM and the hypervisor. WeSee shows that using | AMD SEV-SNP offers VM-level trusted execution

关键词： Privacy | Virtual machine monitors | Codes | Firewalls (computing) | Registers | Security | Kernel

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Firecracker is a virtual machine manager (VMM | ) purpose-built by AWS for serverless cloud platforms | - services that run code for thousands of end users on a | per-task basis, automatically managing server | infrastructure. In addition to architectural attacks, AWS

关键词： System security | Microarchitectural security | Virtual machines | Hypervisor | Serverless | Cloud systems

摘要： the hypervisor configuration files that are | In the XANDAR project, a holistic model-based | toolchain has been formulated that follows the X-by | -Construction (XbC) paradigm i.e., a "step-wise refinement | from specifications to executable code" that results

关键词： Code optimizations | HEFT scheduling | EDF scheduling | Hypervisor | Software components | Runnables

摘要： host before triggering virtual machine monitor | virtual computing system, potentially leading to system | migrate virtual machines from operating host to backup | Software aging can impact the efficiency of a | crashes or failures over time. A well-defined approach

关键词： Virtual machine monitor | Software aging | Software rejuvenation | Semi-Markov | Regenerative Process | Steady State Performance

摘要： softwarization and virtualization, virtual software-defined | the placement to the dynamically changing virtual | hypervisor. In a resilient optical control plane each | hypervisor instance through short control paths, which | propose an intelligent greedy hypervisor placement

关键词： Machine learning | Resilient hypervisor placement | Self-adjusting algorithms | Virtual software-defined optical networks

摘要： Viewpoint Modeling with Multi-task learning (VMM) that | datasets, VeRI and VeRI-Wild, demonstrate that VMM | existing methods with similar network scales, VMM | Vehicle Re-Identification (V-ReID) is a | crucial research topic in the field of intelligent

关键词： Vehicle re-Identification | Representation learning | Multi-Task learning | Feature decoupling

摘要：, applications run on a separation kernel hypervisor, a | hypervisor, enhancing system performance. Our proposed | handled by the hypervisor and which ones by the guest | hypervisor intervention, matching the performance when non | © 2024 The AuthorsThe increasing complexity of

关键词： Full virtualization | Hardware assisted virtualization | LEON processor | On-board systems

摘要： (VMM) operations can be achieved through the | the efficient realization of VMM operations. The | Edge inference chips based on non-volatile | memory hold promise in mitigating the bottleneck | attributed to substantial data movement in artificial

关键词： Memristor crossbar | Interface circuit | ASIC | SC-LNO memristor | TIA

摘要：-scale vector-matrix multiplication (VMM) operations | Neuromorphic hardware using nonvolatile analog | synaptic devices provides promising advantages of | reducing energy and time consumption for performing large | . However, the reported training methods for neuromorphic

关键词： Hardware | Training | Neuromorphics | Tuning | Nonvolatile memory | Neural networks | Protocols

摘要： root privileges. Commodity virtual machine | potential of the thin hypervisor technique on the flagship | experimental result shows that our prototype hypervisor has a | HPC clusters do not currently provide root | priv-ileges on the operating system to users, however

关键词： Degradation | Virtual machine monitors | Conferences | Prototypes | Cluster computing | Kernel | Tuning

摘要： hypervisor controlled by the cloud provider. AMD introduced | communication between the VM and the untrusted hypervisor. We | present WeSee attack, where the hypervisor injects | the VM and the hypervisor. WeSee shows that using | AMD SEV-SNP offers VM-level trusted execution

关键词： Privacy | Virtual machine monitors | Codes | Firewalls (computing) | Registers | Security | Kernel

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： the hypervisor* configuration files that are* | In the XANDAR project, a holistic model-based | toolchain has been formulated that follows the X-by | -Construction (XbC) paradigm i.e., a "step-wise refinement | from specifications to executable code" that results

摘要： host before triggering virtual machine monitor | virtual computing system, potentially leading to system | migrate virtual* machines from operating host to backup* | Software aging can impact the efficiency of a | crashes or failures over time. A well-defined approach

摘要： softwarization and virtualization, virtual* software-defined* | the placement to the dynamically changing virtual | hypervisor. In a resilient optical control plane each | hypervisor instance through short control paths, which | propose an intelligent greedy hypervisor* placement*

摘要：, applications run on a separation kernel hypervisor, a | hypervisor, enhancing system performance. Our proposed | handled by the hypervisor* and which ones by the guest* | hypervisor intervention, matching the performance when non | © 2024 The AuthorsThe increasing complexity of

摘要： (VMM) operations can be achieved through the | the efficient realization of VMM* operations. The* | Edge inference chips based on non-volatile | memory hold promise in mitigating the bottleneck | attributed to substantial data movement in artificial

摘要： root privileges. Commodity virtual machine | potential of the thin hypervisor* technique on the flagship* | experimental result shows that our prototype hypervisor* has a* | HPC clusters do not currently provide root | priv-ileges on the operating system to users, however

摘要： hypervisor controlled by the cloud provider. AMD introduced | communication between the VM and the untrusted hypervisor. We | present WeSee attack, where the hypervisor* injects* | the VM and the hypervisor. WeSee shows that using | AMD SEV-SNP offers VM-level trusted execution