Entropy-Based Anomaly Detection for Memory Integrity Preservation in Multi-Agent Systems
Frontiers in Artificial Intelligence Research · 2026-03-25 · 3 (2) · 33-42
DOI: 10.71465/fair757 ↗At a glance
Journal article in Frontiers in Artificial Intelligence Research, published online on 2026-03-25. Written by Lukas Meier and 2 co-authors. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Memory poisoning often alters statistical properties of shared state representations. This study proposes an entropy-based monitoring mechanism to detect anomalous memory distributions in collaborative agent environments. Shannon entropy and conditional entropy metrics are computed over memory state vectors at each synchronization step. A divergence threshold based on Kullback–Leibler distance identifies suspicious memory updates. Experiments were conducted on distributed planning simulations with 150 agents and controlled poisoning injection rates from 5% to 30%. Detection precision reached 93.1% and recall 88.7% at a divergence threshold of 0.27. Early intervention reduced system-wide contamination by 48.3% compared with no monitoring. Entropy-driven detection provides a lightweight and scalable solution for preserving memory integrity.
Cite
APA
Meier, L., Morel, C., & Schmid, A. (2026). Entropy-Based Anomaly Detection for Memory Integrity Preservation in Multi-Agent Systems. Frontiers in Artificial Intelligence Research, 3(2), 33-42. https://doi.org/10.71465/fair757
Vancouver
Meier L, Morel C, Schmid A. Entropy-Based Anomaly Detection for Memory Integrity Preservation in Multi-Agent Systems. Frontiers in Artificial Intelligence Research. 2026;3(2):33-42. doi:10.71465/fair757
BibTeX
@article{Meier2026,
author = {Meier, Lukas and Morel, Camille and Schmid, Adrian},
title = {Entropy-Based Anomaly Detection for Memory Integrity Preservation in Multi-Agent Systems},
journal = {Frontiers in Artificial Intelligence Research},
year = {2026},
volume = {3},
number = {2},
pages = {33--42},
doi = {10.71465/fair757}
}
EUVIMED