24 February 2023 in IEEE Transactions on Computational Imaging
A new Polarimetric Interferometry Inverse Synthetic Aperture Radar (Pol-InISAR) 3D imaging method for non-cooperative targets is proposed in this paper. 3D imaging of non-cooperative targets becomes possible by combining additional information of interferometric phase along with conventional 2D ISAR imaging. In the previously reported single-polarimetry InISAR based 3D imaging, only a single-channel based interferometric phase is available that can be exploited to reconstruct the 3D ISAR image. This limits the ability to obtain a full target's scattering response and therefore limits the estimation of an accurate interferometric phase. To overcome this constraint, full-polarimetry information is being exploited in this paper, which allows to select the optimal polarimetric combination through which the highest coherence can be obtained. A higher coherence leads to a reduction (optimally a minimization) of the phase estimation error. Consequently, with an optimal phase estimation, an accurate 3D imaging of the target is possible. To validate this proposed Pol-InISAR based 3D imaging approach, both simulated and real datasets are taken under consideration.
8 January 2025 in IEEE Transactions on Radar Systems
Three-Dimensional Interferometric Synthetic Aperture Radar (3D-InISAR) imaging provides a more complete and reliable representation of targets compared to traditional 2D-ISAR, overcoming limitations related to the geometry of the radar-target system and relative motion. This paper presents the application of a Point Cloud Transformer (PCT) for Automatic Target Recognition (ATR) using 3D-InISAR data. The PCT model, originally developed to classify LIDAR’s point clouds, is trained on sparse synthetic point cloud datasets representing various military vehicles, including cars, tanks, and trucks. The synthetic data is carefully generated from CAD models, incorporating techniques such as voxel downsampling and data augmentation to ensure high fidelity and diversity. Initial testing on synthetic data demonstrates the PCT’s robustness and high accuracy when used for ATR. To bridge the gap between synthetic and real data, a transfer learning approach is employed, which operates a fine-tuning on the pre-trained model by using real 3D-InISAR point clouds obtained from the publicly available SDMS-AFRL dataset. Results show significant improvements in classification accuracy post fine-tuning, validating the effectiveness of the PCT model for real-world ATR applications. The findings highlight the potential of transformer-based models in enhancing target recognition systems for future ATR systems based on 3D radar images.
22 April 2024 in IEEE Transactions on Radar Systems
The Three-Dimensional Interferometric Inverse Synthetic Aperture Radar Imaging (3D InISAR) method tackles the interpretability challenges associated with two-dimensional ISAR. It achieves this by providing a 3D representation of the target, offering a more comprehensive understanding of its shape and features. However, this approach faces challenges related to interferometric measurement ambiguity, especially in operational scenarios where factors such as target type and range of the target come into play. Conventional methods for interferogram unwrapping used in Interferometric SAR systems for topographic mapping cannot be directly applied to man-made objects in ISAR due to the discrete nature of ISAR imaging, which violates the assumption of spatial continuity. To address these issues, various multi-receiver solutions have been proposed in the literature. This paper introduces a different approach: a maximum likelihood-based dual-frequency technique applied to 3D InISAR imaging. Leveraging the frequency diversity inherent in a wideband receiver and utilizing two non-overlapping sub-bandwidths, this method effectively resolves measurement ambiguity. Testing the method in a simulated scenarios highlights the enhanced reconstruction abilities of the method and the benefits of utilizing extended physical baselines.
18 November 2024 in IEEE Access
The state of the art in deepfake technology demonstrates rapid technological evolution. Machine learning algorithms are becoming increasingly talented at generating synthetic yet realistic media, raising ethical, social security, and political concerns. Concurrently, the increasing frequency of supply chain attacks and Advanced Persistent Threats (APTs) poses an evolving threat to the security of critical infrastructure, drawing the attention of state-level actors. Our research on AI-generated threats explores the fabrication of images that depict non-existent events, demonstrating the ability to create false radar images. Specifically, counterfeit Inverse Synthetic Aperture Radar (ISAR) images, created using Generative Adversarial Networks (GANs), closely resemble real targets and present a significant threat to maritime operations when exploited in supply chain attacks or by APTs. Radar systems are one of the main elements of ship navigational chains that provide vital information on the surrounding area in terms of distance and speed. Real data analysis in this paper has been conducted on an ISAR database extracted from the NATO SET-196 trials, demonstrating the capability of GANs to create convincing fake ISAR images. Such experiments raise awareness of the vulnerabilities of imaging radar systems to novel, AI-generated cyberattacks.
18 October 2023 in TechRxiv
Navigational systems, the heart of maritime oper- ations, face escalating cybersecurity risks due to their system of systems nature and reliance on diverse suppliers. Amid concerns about supply chain attacks and insider threats, the potential for malicious radar image injections, including Inverse Synthetic Aperture Radar (ISAR) images, is emerging. Such manipulations can critically undermine navigational integrity through the generation of decoy targets, the strategic relocation of existing ones, and the effective concealment of additional targets. We have identified where an Advanced Persistent Threat (APT) could be concealed within the processing chain of a modern radar system. This study demonstrates the potential of APTs to exploit Generative Adversarial Networks (GANs) for the creation of deceptive ISAR images, thereby spotlighting this previously unexplored threat vector. Our findings offer novel insights into bolstering maritime cybersecurity in an increasingly AI-dominated landscape.