# Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers

arXiv: https://arxiv.org/abs/2609.06514 · HTML: https://mlsanity.com/paper/2609.06514/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Corralling a Band of Bandit Algorithms](https://mlsanity.com/paper/1612.06246/) (2016)
- [Model Selection in Contextual Stochastic Bandit Problems](https://mlsanity.com/paper/2003.01704/) (2020)
- [Model selection for contextual bandits](https://mlsanity.com/paper/1906.00531/) (2019)
- [Constrained Contextual Bandit Learning for Adaptive Radar Waveform Selection](https://mlsanity.com/paper/2103.05541/) (2021)
- [Universal and data-adaptive algorithms for model selection in linear contextual bandits](https://mlsanity.com/paper/2111.04688/) (2021)
- [LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits](https://mlsanity.com/paper/2403.03219/) (2024)
- [Towards Optimal Adaptive Wireless Communications in Unknown Environments](https://mlsanity.com/paper/1505.06608/) (2015)
- [FOLPETTI: A Novel Multi-Armed Bandit Smart Attack for Wireless Networks](https://mlsanity.com/paper/2205.03915/) (2022)

## Abstract (arXiv)

Adaptive frequency hopping against predictive jamming must address both model uncertainty and policy exposure: the context-loss relationship may vary across operating regimes, while persistent hopping patterns may expose high-probability channels to attack. We propose D-PACT-AFH, a model-adaptive and risk-constrained adversarial contextual-bandit framework in which a Tsallis-FTRL master combines a global linear learner with a partitioned local learner and selects the model class online. D-PACT-Hit incorporates channel-wise marginal hit risk into model selection, while D-PACT-Safe applies a minimum-Kullback-Leibler projection to enforce a per-slot risk budget. We establish estimator validity under non-anticipating attacks, an oracle decomposition relative to the better fixed base, and an exact conditional-risk guarantee for the Safe projection. Experiments across diverse channel regimes and jammer types demonstrate effective model adaptation and a controllable goodput-risk tradeoff: D-PACT-AFH recovers 95.5% of the local learner's gain under observable switching while avoiding 77.7% of its degradation in a negative-control regime.