The Privacy and Security Risks of Edge LLM Optimization

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

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.