cd/entity/CIMemories· home› entities› CIMemories
grep -l @cimemories /news/*.json | wc -l → 1

CIMemories

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

10:40
2026-08-18
schneier.com
large-language-models

LLMs and Contextual Integrity

A new benchmark called CIMemories, presented in a paper on arXiv, reveals that frontier large language models leak sensitive information from persistent memory in up to 69% of attribute-level violatio…

// co-occurs with top 2 entities
arXiv 1 GPT-5 1
// topics top 3 topics
large language models 1 ai safety 1 ai research 1