NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#edge-llm

1 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedapple-m41 chain-of-thought1 llm-security1 model-optimization1 provenance1 retrieval1 security-drift1 srcot1

2 stories, newest first · one card per story

arXiv cs.CR1d ago

Paper argues edge LLM optimization can open new attack surfaces

The abstract says cutting memory, compute and energy can change representations, decision pathways and trust boundaries.

edge-llm model-optimization

arXiv cs.AI / cs.LG / cs.CL14d ago

Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs

SRCoT is a local retrieve-reflect-revise pipeline for source-labeled LLM outputs, shown only in synthetic case studies.

srcot chain-of-thought

1