Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond

Yalin E. Sagduyu; Tugba Erpek; Sastry Kompella

cs.NIOct 29, 2026

Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond

Authors: Yalin E. Sagduyu, Tugba Erpek, Sastry Kompella

Organizations: Nexcepta, Gaithersburg, MD, USA

Abstract

Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources. While multistatic ISAC can increase sensing coverage with spatially distributed receivers, dense and dynamic clutter can significantly degrade bistatic range and Doppler estimation, leading to errors in target localization and velocity estimation. This paper presents a multistatic ISAC framework with clutter suppression for high-fidelity estimation of target position and velocity. Distributed clutter is modeled with randomly located scatterers with varying Doppler spreads and radar cross sections to capture dense and dynamic clutter effects. A broad range of conventional signal processing baselines are evaluated for clutter suppression, showing limited robustness under strong clutter conditions. To address this limitation, deep learning-based clutter suppression methods are introduced to improve robustness against dense and dynamic clutter by employing residual and attention-enhanced deep neural network architectures that directly enhance target responses from clutter-contaminated observations. These methods substantially outperform conventional approaches in target position and velocity estimation across diverse clutter conditions in multistatic ISAC.

Figures & tables

Fig. 1 : Multistatic ISAC in clutter environment.

Method	RX	$B_{\rm true}$	$B_{\rm est}$	$B_{\rm err}$	$v_{\rm true}$	$v_{\rm est}$	$v_{\rm err}$
NCS	1	331.16	293.11	-38.05	-25.61	-2.17	23.44
NCS	2	422.90	292.80	-130.09	-13.86	5.82	19.69
NCS	3	533.39	312.32	-221.07	-49.05	6.85	55.91
RMHP	1	331.16	331.75	0.58	-25.61	-25.61	-0.00
RMHP	2	422.90	429.64	6.74	-13.86	-13.88	-0.01
RMHP	3	533.39	312.53	-220.85	-49.05	7.04	56.10

TABLE I : Per-receiver bistatic range and radial-velocity estimation results.

Method	RMS $B$ Error (m)	Position Error (m)	Speed Error (m/s)	Angle Error (deg)
NCS	149.715	114.985	22.184	114.065
RMHP	127.570	158.673	9.509	156.948
DLCS-1	5.122	4.462	0.445	0.045

TABLE II : Localization and velocity estimation errors.

Panel of Figure 4 — Fig. 2 : Velocity estimation results.

Panel of Figure 5 — Fig. 3 : Target localization results.

Panel of Figure 6 — Fig. 4 : Bistatic range-Doppler maps.

$N_{c}$	$\alpha_{c}$	$\sigma_{f,c}$	NCS	SP-AD	SP-R1	DPSS	CMTD	TVHP	RMHP	WHP	ALMS	POLYHP	DLCS-1
40	2	30 Hz	1.72%	24.30%	1.72%	2.62%	1.72%	18.41%	25.70%	10.56%	10.23%	2.62%	62.77%
40	1	30 Hz	2.86%	35.27%	3.03%	5.16%	3.52%	29.46%	35.11%	18.74%	17.92%	5.65%	74.39%
20	2	30 Hz	2.85%	36.92%	3.83%	5.62%	3.26%	28.61%	40.18%	22.00%	19.89%	5.62%	72.21%
20	1	30 Hz	5.46%	46.70%	6.68%	10.35%	6.03%	38.30%	48.17%	32.19%	29.99%	10.51%	80.93%
40	1	10 Hz	2.29%	65.90%	5.40%	29.84%	4.09%	59.93%	85.61%	54.62%	46.85%	2.62%	90.27%
20	1	10 Hz	4.97%	73.94%	11.64%	46.42%	9.77%	65.55%	89.98%	68.08%	62.87%	43.08%	94.22%

TABLE III : Normalized success rate

\eta_{\text{succ}}

for different clutter-suppression methods.

$N_{c}$	$\alpha_{c}$	$\sigma_{f,c}$	$N_{\mathrm{train}}$	$N_{\mathrm{epoch}}$	DLCS-1	DLCS-2
40	2	30 Hz	500	200	$62.77\%$	$66.61\%$
40	2	30 Hz	5000	500	$71.19\%$	$72.42\%$
40	1	30 Hz	500	200	$74.39\%$	$78.48\%$
40	1	30 Hz	5000	500	$80.44\%$	$84.29\%$
20	2	30 Hz	500	200	$72.21\%$	$74.16\%$
20	2	30 Hz	5000	500	$76.69\%$	$78.24\%$

TABLE IV : Normalized success rate comparison of DLCS-1 and DLCS-2.

Panel of Figure 9 — Fig. 5 : Normalized success rate $\eta_{\text{succ}}$ versus position error threshold $T$ (m).

Integrated Sensing and Communication

Integrated sensing and communication combines wireless data links with radar-like perception using shared signals, spectrum, and hardware.

See all 48 papers

Deep Learning-Driven Friendly Jamming for Secure Multicarrier ISAC Under Channel Uncertainty
Mar 5, 2026Bui Minh Tuan, Van-Dinh Nguyen, Diep N. Nguyen +5Wireless Communications Integrated Sensing and Communication
the School of Electrical and Data Engineering, University of Technology Sydney, NSW 2007, Australia · the School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, D02PN40, Ireland · Smart Green Transformation Center (GREEN-X), VinUniversity, Hanoi, Vietnam +3
Resolving Multi-Target Association in OFDM-based ISAC via Vision-aided Multi-Modal Learning
Jun 20, 2026Meng Hua, Chenghong Bian, Deniz GunduzIntegrated Sensing and Communication Wireless Communications
Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, U.K. · Department of Electrical and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong.
Task-Oriented Candidate-Latent Feedback for Coarse-to-Fine Sensing in Distributed OFDM-ISAC Networks
Aug 4, 2026Shiv Shankar, Radha Krishna Ganti, J Klutto MillethIntegrated Sensing and Communication
Indian Institute of Technology (IIT), Madras, Chennai India · Centre of Excellence in Wireless Technology (CEWiT), Chennai India

Mar 5, 2026J/K move · Enter open · S save

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

Bui Minh Tuan, Van-Dinh Nguyen, Diep N. Nguyen, Nguyen Linh Trung+4

the School of Electrical and Data Engineering, University of Technology Sydney, NSW 2007, Australia · the School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, D02PN40, Ireland · Smart Green Transformation Center (GREEN-X), VinUniversity, Hanoi, Vietnam+3

Wireless Communications Integrated Sensing and Communication

Open paper AskPDF arXiv

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.

Abstract

Integrated Sensing and Communication

Explore similar work

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

Resolving Multi-Target Association in OFDM-based ISAC via Vision-aided Multi-Modal Learning

Task-Oriented Candidate-Latent Feedback for Coarse-to-Fine Sensing in Distributed OFDM-ISAC Networks