Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Driven Friendly Jamming for Secure Multicarrier ISAC Under Channel Uncertainty

Bui Minh Tuan, Van-Dinh Nguyen, Diep N. Nguyen, Nguyen Linh Trung, Nguyen Van Huynh, Dinh Thai Hoang, Marwan Krunz, Eryk Dutkiewicz

TL;DR

A radar-aware neural network that jointly optimizes beamforming and jamming by integrating a novel nonparametric Fisher Information Matrix (FIM) estimator based on f-divergence is proposed, which achieves significant improvements in secrecy rate, reduced block error rate (BLER), and strong robustness against CSI uncertainty and angular estimation errors.

Abstract

Integrated sensing and communication (ISAC) systems promise efficient spectrum utilization by jointly supporting radar sensing and wireless communication. This paper presents a deep learning-driven framework for enhancing physical-layer security in multicarrier ISAC systems under imperfect channel state information (CSI) and in the presence of unknown eavesdropper (Eve) locations. Unlike conventional ISAC-based friendly jamming (FJ) approaches that require Eve's CSI or precise angle-of-arrival (AoA) estimates, our method exploits radar echo feedback to guide directional jamming without explicit Eve's information. To enhance robustness to radar sensing uncertainty, we propose a radar-aware neural network that jointly optimizes beamforming and jamming by integrating a novel nonparametric Fisher Information Matrix (FIM) estimator based on f-divergence. The jamming design satisfies the Cramer-Rao lower bound (CRLB) constraints even in the presence of noisy AoA. For efficient implementation, we introduce a quantized tensor train-based encoder that reduces the model size by more than 100 times with negligible performance loss. We also integrate a non-overlapping secure scheme into the proposed framework, in which specific sub-bands can be dedicated solely to communication. Extensive simulations demonstrate that the proposed solution achieves significant improvements in secrecy rate, reduced block error rate (BLER), and strong robustness against CSI uncertainty and angular estimation errors, underscoring the effectiveness of the proposed deep learning-driven friendly jamming framework under practical ISAC impairments.

Deep Learning-Driven Friendly Jamming for Secure Multicarrier ISAC Under Channel Uncertainty

TL;DR

A radar-aware neural network that jointly optimizes beamforming and jamming by integrating a novel nonparametric Fisher Information Matrix (FIM) estimator based on f-divergence is proposed, which achieves significant improvements in secrecy rate, reduced block error rate (BLER), and strong robustness against CSI uncertainty and angular estimation errors.

Abstract

Integrated sensing and communication (ISAC) systems promise efficient spectrum utilization by jointly supporting radar sensing and wireless communication. This paper presents a deep learning-driven framework for enhancing physical-layer security in multicarrier ISAC systems under imperfect channel state information (CSI) and in the presence of unknown eavesdropper (Eve) locations. Unlike conventional ISAC-based friendly jamming (FJ) approaches that require Eve's CSI or precise angle-of-arrival (AoA) estimates, our method exploits radar echo feedback to guide directional jamming without explicit Eve's information. To enhance robustness to radar sensing uncertainty, we propose a radar-aware neural network that jointly optimizes beamforming and jamming by integrating a novel nonparametric Fisher Information Matrix (FIM) estimator based on f-divergence. The jamming design satisfies the Cramer-Rao lower bound (CRLB) constraints even in the presence of noisy AoA. For efficient implementation, we introduce a quantized tensor train-based encoder that reduces the model size by more than 100 times with negligible performance loss. We also integrate a non-overlapping secure scheme into the proposed framework, in which specific sub-bands can be dedicated solely to communication. Extensive simulations demonstrate that the proposed solution achieves significant improvements in secrecy rate, reduced block error rate (BLER), and strong robustness against CSI uncertainty and angular estimation errors, underscoring the effectiveness of the proposed deep learning-driven friendly jamming framework under practical ISAC impairments.
Paper Structure (22 sections, 1 theorem, 42 equations, 12 figures, 3 tables, 1 algorithm)

This paper contains 22 sections, 1 theorem, 42 equations, 12 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Motivation and Main Contributions
  4. Paper Organization and Notations
  5. Friendly Jamming-enabled Secure Single-Carrier ISAC
  6. System Model
  7. Problem Formulation of Single-carrier ISAC-FJ
  8. FJ-based Fisher Information Estimation
  9. Learning-based FJ for ISAC Framework
  10. Friendly Jamming Secure Multicarrier ISAC
  11. Multicarrier MIMO-OFDM System Model
  12. Problem Formulation of Overlap Multicarrier ISAC-FJ
  13. Imperfect Angle Estimation Model
  14. Data-Driven Multicarrier FIM Estimation
  15. Quantized Tensor-Train Based Neural Compression
  16. ...and 7 more sections

Key Result

Theorem 1

Consider the received radar echo on subcarrier $n \in \mathcal{S}_r$ modeled as where $\boldsymbol{\vartheta}$ collects the angular parameters (e.g., AoA), $\mathbf G(\boldsymbol{\vartheta})$ is the array/system response, and $\mathbf S_r[n]\in\mathbb C^{N_t\times T}$ is the OFDM probing matrix with $N_t$ antennas and $T$ time slots. By defining $\mathbf A_\omega := \tfrac{\par It is clear that $

Figures (12)

  • Figure 1: Two multicarrier ISAC architectures considered in this work. In the overlapping scheme, all subcarriers are jointly used for communication, sensing, and friendly jamming. In the non-overlapping scheme, the subcarriers are partitioned into disjoint sets, with one set allocated to communication and the remaining set used for sensing and friendly jamming.
  • Figure 2: ISAC FJ workflow: (1) message encoding, (2) beamforming generation, (3) power-normalized transmission, (4) radar echo acquisition, (5) Fisher information estimation, (6) friendly jamming optimization, and (7) message decoding. The dashed arrow highlights the sensing feedback loop, which enables adaptive jamming without requiring explicit eavesdropper CSI.
  • Figure 3: Sum secrecy rate comparison with perfect AoA estimation.
  • Figure 4: BLER on the legitimate channel.
  • Figure 5: Convergence of training process.
  • ...and 7 more figures

Theorems & Definitions (2)

  • Theorem 1: Waveform-agnostic FIM for OFDM probing
  • proof : Proof sketch