← 研踪 PaperTrailarXiv:2610.40543 · v1
The Privacy and Security Risks of Edge LLM Optimization
首次提交 2026-10-30 01:36
版本更新 2026-10-30 01:36
雷达观测 2026-10-30 13:28
摘要
Edge deployment of Large Language Models requires optimization techniques that reduce memory, computation, and energy costs. However, preserving task performance does not necessarily preserve security. We argue that optimization is an information transformation that can alter representations, decision pathways, and trust boundaries, creating security drift and optimization-induced attack surfaces.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-30 01:36 · 最新观测版本
The Privacy and Security Risks of Edge LLM Optimization
Edge deployment of Large Language Models requires optimization techniques that reduce memory, computation, and energy costs. However, preserving task performance does not necessarily preserve security. We argue that optimization is an information transformation that can alter representations, decision pathways, and trust boundaries, creating security drift and optimization-induced attack surfaces.
查看此版本解读 →查看此版本原文 ↗