Frequency-Domain Characterization of Memory Poisoning Propagation in Multi-Agent Collaborative Systems
Frontiers in Applied Physics and Mathematics · 15.03.2026 · 3 (2) · 44-52
DOI: 10.71465/fapm760 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Applied Physics and Mathematics, online erschienen am 15.03.2026. Verfasst von Wei Ming Tan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Memory poisoning in multi-agent collaborative systems may exhibit structured propagation patterns across communication channels. This study analyzes poisoning diffusion using frequency-domain decomposition of inter-agent memory update signals. Memory state transitions are transformed via discrete Fourier analysis to identify anomalous high-frequency components introduced by adversarial perturbations. A spectral attenuation filter selectively suppresses abnormal frequency bands before synchronization. Experiments were conducted on 120-agent distributed coordination tasks over 10,000 update cycles. Poisoning injection at 15% intensity increased high-frequency spectral energy by 63.2% compared to clean baselines. Spectral filtering reduced contamination spread from 58.4% to 19.6% of agents and restored task performance to 87.3% of nominal levels. Frequency-domain modeling provides a novel perspective on poisoning detection and containment in collaborative agent systems.
Zitieren
APA
Tan, W. M., Lim, C., & Lee, J. (2026). Frequency-Domain Characterization of Memory Poisoning Propagation in Multi-Agent Collaborative Systems. Frontiers in Applied Physics and Mathematics, 3(2), 44-52. https://doi.org/10.71465/fapm760
Vancouver
Tan WM, Lim C, Lee J. Frequency-Domain Characterization of Memory Poisoning Propagation in Multi-Agent Collaborative Systems. Frontiers in Applied Physics and Mathematics. 2026;3(2):44-52. doi:10.71465/fapm760
BibTeX
@article{Tan2026,
author = {Tan, Wei Ming and Lim, Cheryl and Lee, Jonathan},
title = {Frequency-Domain Characterization of Memory Poisoning Propagation in Multi-Agent Collaborative Systems},
journal = {Frontiers in Applied Physics and Mathematics},
year = {2026},
volume = {3},
number = {2},
pages = {44--52},
doi = {10.71465/fapm760}
}
EUVIMED