PERSIST : Threat Modeling Memory‐Persistent AI Agents in Cloud‐to‐Edge Environments

Abstract

Agentic artificial intelligence systems increasingly depend on persistent runtime memory, including vector databases, episodic memory stores, long‐term retrieval indices, and cloud‐to‐edge replicas. Existing security frameworks address prompt injection, data poisoning, and model‐level risks, but they do not fully model persistent memory as an active behavioral surface whose records can be written, synchronized, retrieved, transformed, revoked, and later used as decision context. This article i

Categories

Framework mappings

Suggested from the entry's categories.

@article{brobbey2026persist,
  title = {{PERSIST
 : Threat Modeling Memory‐Persistent
 AI
 Agents in Cloud‐to‐Edge Environments}},
  author = {Albert Adusei Brobbey and Narayan P. Bhosale},
  year = {2026},
  month = sep,
  journal = {Security and Privacy},
  doi = {10.1002/spy2.70248},
  url = {https://www.semanticscholar.org/paper/2b34f27f1c8e827f22f4e6d347c008446794b992}
}