arXiv (All)
open access
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Sparse attention is widely used to accelerate long-context inference in modern large language models (LLMs), but its input-dependent execution behavior introduces previously unexplored privacy risks. We identify a new GPU micro-architectural side channel, termed Sparsity-Induced Memory Access (SIMA)
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs#1136792
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- NOSA: Native and Offloadable Sparse Attention#1129124
- The Correctness Illusion in LLM-Generated GPU Kernels#290549
- Dissecting GPU Utilization for LLM Inference on Nvidia Hopper#1070372
Record · ID 1143431
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive