English(EN) Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

行锤击攻击放大LLM推理延迟和成本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了LLVMhammer，一种新颖的行锤击（Rowhammer）攻击，它针对GPU上大型语言模型（LLM）推理的延迟和成本。通过在CPU的DRAM中引发比特翻转，该攻击导致Triton JIT编译框架生成次优的GPU内核，从而导致推理延迟增加。这种4-16%的减速会转化为多GPU部署更高的运营成本。该攻击与GPU无关，并且还会损坏LLM的输出，影响BERTScore等指标。 AI

影响突出了LLM推理管道中潜在的安全漏洞，影响成本和可靠性。

排序理由详细介绍LLM推理中新颖安全漏洞的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM推理中新颖安全漏洞的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Mrityunjay Shukla, Shubham Roy, Biswabandan Panda · 2026-10-23 04:00

Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

arXiv:2610.30798v1 Announce Type: cross 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 …

本文如何被排名

报道来源 [1]

Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

相关实体

相关话题