PyJama: Differentiable Jamming and Anti-Jamming with NVIDIA Sionna

TL;DR

PyJama is an open-source library that enables differentiable simulation of jamming and anti-jamming in wireless systems, facilitating research on machine learning-based attack and defense strategies.

Contribution

It introduces PyJama, a novel framework integrated with NVIDIA Sionna, for realistic simulation and learning of jamming and anti-jamming techniques in wireless communications.

Findings

PyJama supports complex MIMO and OFDM simulations with realistic channel models.

It enables learning jamming strategies using gradient-based optimization.

Learned jamming strategies are effective, non-trivial, and interpretable.

Abstract

Despite extensive research on jamming attacks on wireless communication systems, the potential of machine learning for amplifying the threat of such attacks, or our ability to mitigate them, remains largely untapped. A key obstacle to such research has been the absence of a suitable framework. To resolve this obstacle, we release PyJama, a fully-differentiable open-source library that adds jamming and anti-jamming functionality to NVIDIA Sionna. We demonstrate the utility of PyJama (i) for realistic MIMO simulations by showing examples that involve forward error correction, OFDM waveforms in time and frequency, realistic channel models, and mobility; and (ii) for learning to jam. Specifically, we use stochastic gradient descent to optimize jamming power allocation over an OFDM resource grid. The learned strategies are non-trivial, intelligible, and effective.