cs.ARDec 25, 2025

Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study

Authors: Duo Chai, Zizhen Liu, Shuhuai Wang, Songwei Pei, Cheng Liu, Huawei Li, Shangguang Wang

Organizations: School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China. · State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

Abstract

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors, particularly in radiation-prone environments such as satellite computing scenarios. While prior work has examined GPU soft errors, most studies have focused on general-purpose applications or conventional neural networks primarily used for vision tasks such as classification and detection. However, vulnerability analysis of modern LLMs remains limited, despite their rapid adoption in diverse application scenarios. Given the unique characteristics of LLMs, their resilience to soft errors may differ substantially from earlier models. To bridge this gap, we conduct the first instruction-level fault injection study of LLM inference to analyze the factors affecting LLM vulnerability. Our approach reveals reliability characteristics from multiple perspectives, highlighting the effects of model architecture, parameter scale, and task complexity. These findings provide new insights into LLM reliability and inform the design of more effective fault tolerance mechanisms.

Figures & tables

Explore similar work

CardsList
  1. Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference

    Jun 1, 2026Yafan Huang, Sheng Di, Guanpeng Lierror propagation in large language model inferenceLLM Inference

  2. An Empirical Study of Issues in GPU Kernel Libraries for LLM Systems

    Nov 6, 2026Yanjie Gao, Jiayi Bi, Haoxiang Lin +1GPU Kernel Correctness Verification

  3. Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

    Oct 22, 2026Mrityunjay Shukla, Shubham Roy, Biswabandan PandaLLM SecurityLLM Inference Efficiency