Imagen de Portada

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Yinpeng, Chen, Yitong, Wang, Lixiang, Gu, Jinyu, Hua, Zhichao, Xia, Yubin
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Machine Learning Operating Systems
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AgenTEE: Confidential LLM Agent Execution on Edge Devices
por: Abdollahi, Sina, et al.
Publicado: (2026)

Security, extensibility, and redundancy in the Metabolic Operating System
por: King, Samuel T.
Publicado: (2023)

Securing Cloud File Systems with Trusted Execution
por: Burke, Quinn, et al.
Publicado: (2023)

Goldilocks Isolation: High Performance VMs with Edera
por: Moore, Marina, et al.
Publicado: (2025)

Tyche: Composable Isolation as a Foundation to Manage Trust in the Cloud
por: Ghosn, Adrien, et al.
Publicado: (2025)

Securing Monolithic Kernels using Compartmentalization
por: Lim, Soo Yee, et al.
Publicado: (2024)

The Android Platform Security Model (2023)
por: Mayrhofer, René, et al.
Publicado: (2019)

Analysis of Security in OS-Level Virtualization
por: Ketha, Krishna Sai, et al.
Publicado: (2025)

Automatic ISA analysis for Secure Context Switching
por: Kalani, Neelu S., et al.
Publicado: (2025)

BULKHEAD: Secure, Scalable, and Efficient Kernel Compartmentalization with PKS
por: Guo, Yinggang, et al.
Publicado: (2024)

Evolution of Android's Permission-based Security Model and Challenges
por: Solanki, Rajendra Kumar, et al.
Publicado: (2026)

Tock: From Research to Securing 10 Million Computers
por: Schuermann, Leon, et al.
Publicado: (2026)

Case Study: Securing MMU-less Linux Using CHERI
por: Almatary, Hesham, et al.
Publicado: (2023)

WebAssembly Based Portable and Secure Sensor Interface for Internet of Things
por: Ou, Botong, et al.
Publicado: (2026)

Safe Sharing of Fast Kernel-Bypass I/O Among Nontrusting Applications
por: Beadle, Alan, et al.
Publicado: (2025)

Contextualizing Security and Privacy of Software-Defined Vehicles: A Literature Review and Industry Perspectives
por: De Vincenzi, Marco, et al.
Publicado: (2024)

Guillotine: Hypervisors for Isolating Malicious AIs
por: Mickens, James, et al.
Publicado: (2025)

Beyond Control: Exploring Novel File System Objects for Data-Only Attacks on Linux Systems
por: Zhou, Jinmeng, et al.
Publicado: (2024)

TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone
por: Wang, Xunjie, et al.
Publicado: (2025)

Blindfold: Confidential Memory Management by Untrusted Operating System
por: Li, Caihua, et al.
Publicado: (2024)

B-Side: Binary-Level Static System Call Identification
por: Thévenon, Gaspard, et al.
Publicado: (2024)

UPSS: a User-centric Private Storage System with its applications
por: Bozorgi, Arastoo, et al.
Publicado: (2024)

Physical Memory Attacks and a Memory Safe Management System for Memory Defense
por: Hillel-Tuch, Alon, et al.
Publicado: (2024)

The HitchHiker's Guide to High-Assurance System Observability Protection with Efficient Permission Switches
por: Zhang, Chuqi, et al.
Publicado: (2024)

Fight Hardware with Hardware: System-wide Detection and Mitigation of Side-Channel Attacks using Performance Counters
por: Carnà, Stefano, et al.
Publicado: (2024)

Threadbox: Sandboxing for Modular Security
por: Alhindi, Maysara, et al.
Publicado: (2025)

MOAT: Towards Safe BPF Kernel Extension
por: Lu, Hongyi, et al.
Publicado: (2023)

SyzParam: Introducing Runtime Parameters into Kernel Driver Fuzzing
por: Sun, Yue, et al.
Publicado: (2025)

Biting the CHERI bullet: Blockers, Enablers and Security Implications of CHERI in Defence
por: Faily, Shamal
Publicado: (2025)

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
por: Chu, Kexin, et al.
Publicado: (2025)

Secure and Efficient Access Control for Computer-Use Agents via Context Space
por: Gong, Haochen, et al.
Publicado: (2025)

Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components
por: Sadi, Amir Al, et al.
Publicado: (2026)

Rethinking Provenance Completeness with a Learning-Based Linux Scheduler
por: Mao, Jinsong, et al.
Publicado: (2025)

Plug. Play. Persist. Inside a Ready-to-Go Havoc C2 Infrastructure
por: Di Santo, Alessio
Publicado: (2025)

SoK: Software Compartmentalization
por: Lefeuvre, Hugo, et al.
Publicado: (2024)

CAEC: Confidential, Attestable, and Efficient Inter-CVM Communication with Arm CCA
por: Abdollahi, Sina, et al.
Publicado: (2025)

Retrofitting XoM for Stripped Binaries without Embedded Data Relocation
por: Luo, Chenke, et al.
Publicado: (2024)

To Unpack or Not to Unpack: Living with Packers to Enable Dynamic Analysis of Android Apps
por: Asghari, Mohammad Hossein, et al.
Publicado: (2025)

Sync+Sync: A Covert Channel Built on fsync with Storage
por: Jiang, Qisheng, et al.
Publicado: (2023)

CRISP: Confidentiality, Rollback, and Integrity Storage Protection for Confidential Cloud-Native Computing
por: Hartono, Ardhi Putra Pratama, et al.
Publicado: (2024)