Newest papers

Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

Mrityunjay Shukla, Shubham Roy, Biswabandan Panda · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30798 · open-access PDF

Russian

Большие языковые модели (LLM) достигают высокой эффективности вывода с использованием оптимизированных ядер GPU, генерируемых просто-в-время (JIT) рамками компиляции, такими как Triton. Triton компилирует ядра GPU через трубопровод на основе MLIR/LLVM. Мы исследуем, может ли индуцированный Rowhammer бит-флип в DRAM CPU ухудшить производительность вывода LLM на основе GPU при сохранении корректности выхода. Мы представляем LLVMhammer, первую атаку Rowhammer, которая вызывает замедление вывода LLM, вызывая бит-флип в трубе компиляции Triton.

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JIT) compilation frameworks such as Triton. Triton compiles GPU kernels through an MLIR/LLVM-based pipeline. We investigate whether a Rowhammer-induced bit-flip in the CPU's DRAM can degrade GPU-based LLM inference performance while preserving output correctness. We present LLVMhammer, the first Rowhammer attack that causes LLM inference slowdown by inducing a bit-flip in Triton's compilation pipeline. A bit-flip in a performance-critical optimization pass causes Triton to gene

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30798, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange