Imagen de Portada

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Saini, Abhishek, Jiang, Haolin, Liu, Hang
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Hardware Architecture
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing
por: Han, Husheng, et al.
Publicado: (2024)

On the Vulnerability of FHE Computation to Silent Data Corruption
por: Mu, Jianan, et al.
Publicado: (2026)

GPU Acceleration of TFHE-Based High-Precision Nonlinear Layers for Encrypted LLM Inference
por: Chen, Guoci, et al.
Publicado: (2026)

Shield Bash: Abusing Defensive Coherence State Retrieval to Break Timing Obfuscation
por: Ramkrishnan, Kartik, et al.
Publicado: (2025)

DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
por: Zhou, Ranyang, et al.
Publicado: (2024)

RowPress Vulnerability in Modern DRAM Chips
por: Luo, Haocong, et al.
Publicado: (2024)

Lost and Found in Speculation: Hybrid Speculative Vulnerability Detection
por: Rostami, Mohamadreza, et al.
Publicado: (2024)

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
por: Tyagi, Abhishek, et al.
Publicado: (2022)

Understanding and Mitigating Covert Channel and Side Channel Vulnerabilities Introduced by RowHammer Defenses
por: Bostancı, F. Nisa, et al.
Publicado: (2025)

Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
por: Chai, Duo, et al.
Publicado: (2025)

Side-channel Inference of User Activities in AR/VR Using GPU Profiling
por: Son, Seonghun, et al.
Publicado: (2025)

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems
por: Yamamoto, Yuji, et al.
Publicado: (2026)

APINT: A Full-Stack Framework for Acceleration of Privacy-Preserving Inference of Transformers based on Garbled Circuits
por: Cho, Hyunjun, et al.
Publicado: (2025)

PermuteV: A Performant Side-channel-Resistant RISC-V Core Securing Edge AI Inference
por: Narkthong, Nuntipat, et al.
Publicado: (2025)

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation
por: Rezakhani, Mahshid, et al.
Publicado: (2026)

LaMoS: Enabling Efficient Large Number Modular Multiplication through SRAM-based CiM Acceleration
por: Li, Haomin, et al.
Publicado: (2025)

FireGuard: A Generalized Microarchitecture for Fine-Grained Security Analysis on OoO Superscalar Cores
por: Jiang, Zhe, et al.
Publicado: (2025)

HF-NTT: Hazard-Free Dataflow Accelerator for Number Theoretic Transform
por: Meng, Xiangchen, et al.
Publicado: (2024)

ALLMod: Exploring $\underline{\mathbf{A}}$rea-Efficiency of $\underline{\mathbf{L}}$UT-based $\underline{\mathbf{L}}$arge Number $\underline{\mathbf{Mod}}$ular Reduction via Hybrid Workloads
por: Liu, Fangxin, et al.
Publicado: (2025)

CipherGuard: Compiler-aided Mitigation against Ciphertext Side-channel Attacks
por: Jiang, Ke, et al.
Publicado: (2025)

PCG: Mitigating Conflict-based Cache Side-channel Attacks with Prefetching
por: Jiang, Fang, et al.
Publicado: (2024)

CIBPU: A Conflict-Invisible Secure Branch Prediction Unit
por: Zhou, Zhe, et al.
Publicado: (2025)

OFHE: An Electro-Optical Accelerator for Discretized TFHE
por: Zheng, Mengxin, et al.
Publicado: (2024)

SoK: Fully Homomorphic Encryption Accelerators
por: Zhang, Junxue, et al.
Publicado: (2022)

SEA Cache: A Performance-Efficient Countermeasure for Contention-based Attacks
por: Liu, Xiao, et al.
Publicado: (2024)

PDF: PUF-based DNN Fingerprinting for Knowledge Distillation Traceability
por: Lyu, Ning, et al.
Publicado: (2026)

SoK: Rowhammer on Commodity Operating Systems
por: Zhang, Zhi, et al.
Publicado: (2022)

NTTSuite: Number Theoretic Transform Benchmarks for Accelerating Encrypted Computation
por: Ding, Juran, et al.
Publicado: (2024)

TroLL: Exploiting Structural Similarities between Logic Locking and Hardware Trojans
por: Liu, Yuntao, et al.
Publicado: (2023)

A High Performance and Efficient Post-Quantum Crypto-Processor for FrodoKEM
por: Li, Kai, et al.
Publicado: (2026)

The Road to Trust: Building Enclaves within Confidential VMs
por: Wang, Wenhao, et al.
Publicado: (2024)

μRL: Discovering Transient Execution Vulnerabilities Using Reinforcement Learning
por: Tol, M. Caner, et al.
Publicado: (2025)

EFFACT: A Highly Efficient Full-Stack FHE Acceleration Platform
por: Huang, Yi, et al.
Publicado: (2025)

Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor
por: Miah, Abdullah Arafat, et al.
Publicado: (2024)

Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
por: Chrapek, Marcin, et al.
Publicado: (2025)

FHECore: Rethinking GPU Microarchitecture for Fully Homomorphic Encryption
por: Daksha, Lohit, et al.
Publicado: (2026)

The Avatar Cache: Enabling On-Demand Security with Morphable Cache Architecture
por: Bhatla, Anubhav, et al.
Publicado: (2026)

A New Tool to Find Lightweight (And, Xor) Implementations of Quadratic Vectorial Boolean Functions up to Dimension 9
por: Bolzer, Marie, et al.
Publicado: (2026)

NuRedact: Non-Uniform eFPGA Architecture for Low-Overhead and Secure IP Redaction
por: Das, Voktho, et al.
Publicado: (2026)

GPIR: Enabling Practical Private Information Retrieval with GPUs
por: Ji, Hyesung, et al.
Publicado: (2026)