Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection
Abstract
Effective evaluation of zero-day jamming detectors requires robust adversarial models. However, existing attack models often assume prior knowledge of the target receiver, limiting their utility as evaluation benchmarks. On the detection side, existing detectors fail to capture the global temporal-spectral structure of jamming behavior and cannot differentiate zero-day strategies as they emerge. This paper addresses these limitations through a two-pronged framework. First, an online detection framework is introduced that combines a graph attention network (GAT) for temporal-spectral representation learning with Dirichlet process (DP)-means clustering. This framework jointly classifies known and discovers zero-day strategies within a unified learning objective. Second, an inference-driven reinforcement learning (RL) jammer is proposed as an adversarial benchmark. The jammer treats the target receiver as a black-box, infers the detector state via hypothesis testing, and optimizes the trade-off between attack impact and stealth. Simulation results show that the proposed RL jammer outperforms benchmarks, achieving 33% higher attack efficacy and 67% higher stealth. The proposed detection framework against the proposed RL jammer is shown to achieve 20% higher detection accuracy than the benchmarks.
Related
- ADAPTIVE MULTIRESOLUTION DIFFUSION OPERATORS: A VARIATIONAL THEORY ON EVOLVING MULTIRESOLUTION SPACES
- FOCUS: An Adaptive Fractional Graph-Diffusion Attention Operator, with a Preliminary Hallucination-Warning Application
- Attention-Guided Autoencoder for Retrospective Physiological Anomaly Detection in ICU Vital Signs Using MIMIC-IV Demo Data
- A cascaded U-nets model based on hybrid attention for video anomaly detection
- A prototype-aligned multi-scale attention network for few-shot industrial surface defect detection
BibTeX
@misc{aissou2026coevolving,
title = {{Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection}},
author = {Ghilas Aissou and Rémi A. Chou and Taejoon Kim},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21334},
eprint = {2609.21334},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21334},
}
RIS
TY - UNPB
TI - Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection
AU - Ghilas Aissou
AU - Rémi A. Chou
AU - Taejoon Kim
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21334
UR - https://arxiv.org/abs/2609.21334
AB - Effective evaluation of zero-day jamming detectors requires robust adversarial models. However, existing attack models often assume prior knowledge of the target receiver, limiting their utility as evaluation benchmarks. On the detection side, existing detectors fail to capture the global temporal-spectral structure of jamming behavior and cannot differentiate zero-day strategies as they emerge. This paper addresses these limitations through a two-pronged framework. First, an online detection framework is introduced that combines a graph attention network (GAT) for temporal-spectral representation learning with Dirichlet process (DP)-means clustering. This framework jointly classifies known and discovers zero-day strategies within a unified learning objective. Second, an inference-driven reinforcement learning (RL) jammer is proposed as an adversarial benchmark. The jammer treats the target receiver as a black-box, infers the detector state via hypothesis testing, and optimizes the trade-off between attack impact and stealth. Simulation results show that the proposed RL jammer outperforms benchmarks, achieving 33% higher attack efficacy and 67% higher stealth. The proposed detection framework against the proposed RL jammer is shown to achieve 20% higher detection accuracy than the benchmarks.
ER -