arXiv subjects

Sangarapillai Lambotharan

Publications and source records attributed to Sangarapillai Lambotharan.

At least 19 recordsLinked to original sources

arXiv2026

Beamforming and RIS-Aided Ambient Backscatter Communications with Residual-Feature SVM Detection

Ambient backscatter communication (AmBC) enables battery-free connectivity by modulating data onto existing radio-frequency (RF) signals, eliminating the need for dedicated power sources. However, its reliability degrades when direct wireless channels are obstructed or severely faded. Reconfigurable intelligent surfaces (RISs) offer a solution by creating a favorable propagation environment through the control of the phases of incident signals, thereby strengthening wireless links. This paper investigates an RIS-aided AmBC system that jointly exploits physical-layer reconfiguration and statistical learning to restore detection reliability under such conditions. The RIS phase profile is aligned for the source-RIS-tag link, while a multi-antenna reader applies receive beamforming to steer toward the RF source and the tag separately. At the reader, a hypothesis-based minimum mean square error (MMSE) equalizer reconstructs the ambient symbol under each candidate tag state and produces a pair of residual features, which are classified by a support vector machine (SVM) with a Gaussian kernel. We make the physical-layer-to-learning coupling explicit, i.e., RIS phase alignment and beamforming improve the signal-to-interference-plus-noise ratio (SINR), thereby rendering the residual features more separable and reducing classification error. Simulation results show that the proposed RIS-beamforming-SVM detector achieves substantial bit-error-rate (BER) gains over RIS-energy, SVM, and SVM-beamforming baselines across a wide SINR range, that the spectral-efficiency gains are governed more strongly by the number of RIS elements than by the number of reader antennas, and that performance saturates with a moderate RIS size, allowing near-optimal operation at reduced hardware cost.

eess.SP↗

arXiv2026

Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA

Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive sequentially, because the model must repeatedly adapt without erasing previously retained knowledge. Low-Rank Adaptation (LoRA) offers an efficient way to implement such updates, but naively combining many sequential LoRA modules leads to parameter collision, causing \textit{strong interference} between tasks. We propose a static alternative based on Singular Value Decomposition (SVD)-guided orthogonal subspace projection. Our method constrains each new LoRA update during training so that it lies in the orthogonal complement of the subspaces used by earlier unlearning tasks. This preserves task isolation without requiring dynamic routing at deployment. Experiments on CIFAR-100 with ResNet-20 and on MNIST show stable behavior across long sequences of unlearning tasks. After thirty sequential unlearning tasks, state-of-the-art static fusion reduces retained accuracy from 60.39\% to 12.70\%, whereas the proposed in-training constrained optimization maintains baseline performance ($\sim$58.1\%) while preserving strong unlearning efficacy.

cs.LG↗

arXiv2026

QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation

Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on edge devices, their potential to reduce the energy overhead of fine-tuning remains underexplored. In this work, we propose QuantFL, a sustainable FL framework that leverages pre-trained initialisation to enable aggressive, computationally lightweight quantisation. We demonstrate that pre-training naturally concentrates update statistics, allowing us to use memory-efficient bucket quantisation without the energy-intensive overhead of complex error-feedback mechanisms. On MNIST and CIFAR-100, QuantFL reduces total communication by 40\% ($\simeq40\%$ total-bit reduction with full-precision downlink; $\geq80\%$ on uplink or when downlink is quantised) while matching or exceeding uncompressed baselines under strict bandwidth budgets; BU attains 89.00\% (MNIST) and 66.89\% (CIFAR-100) test accuracy with orders of magnitude fewer bits. We also account for uplink and downlink costs and provide ablations on quantisation levels and initialisation. QuantFL delivers a practical, "green" recipe for scalable training on battery-constrained IoT networks.

cs.LG↗

arXiv2026

Multi-Agent Reinforcement Learning Counteracts Delayed CSI in Multi-Satellite Systems

The integration of satellite communication networks with next-generation (NG) technologies is a promising approach towards global connectivity. However, the quality of services is highly dependant on the availability of accurate channel state information (CSI). Channel estimation in satellite communications is challenging due to the high propagation delay between terrestrial users and satellites, which results in outdated CSI observations on the satellite side. In this paper, we study the downlink transmission of multiple satellites acting as distributed base stations (BS) to mobile terrestrial users. We propose a multi-agent reinforcement learning (MARL) algorithm which aims for maximising the sum-rate of the users, while coping with the outdated CSI. We design a novel bi-level optimisation, procedure themes as dual stage proximal policy optimisation (DS-PPO), for tackling the problem of large continuous action spaces as well as of independent and non-identically distributed (non-IID) environments in MARL. Specifically, the first stage of DS-PPO maximises the sum-rate for an individual satellite and the second stage maximises the sum-rate when all the satellites cooperate to form a distributed multi-antenna BS. Our numerical results demonstrate the robustness of DS-PPO to CSI imperfections as well as the sum-rate improvement attached by the use of DS-PPO. In addition, we provide the convergence analysis for the DS-PPO along with the computational complexity.

cs.IT↗

arXiv2025

DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation

Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under non-independent and identically distributed (non-IID) data, and remain lightweight for edge devices. Prior work either assumes trusted hardware, uses expensive cryptographic tools, or fails to address privacy and robustness simultaneously. We propose DSFL, a Dual-Server Byzantine-Resilient Federated Learning framework that addresses these limitations using a group-based secure aggregation approach. Unlike LSFL, which assumes non-colluding semi-honest servers, DSFL removes this dependency by revealing a key vulnerability: privacy leakage through client-server collusion. DSFL introduces three key innovations: (1) a dual-server secure aggregation protocol that protects updates without encryption or key exchange, (2) a group-wise credit-based filtering mechanism to isolate Byzantine clients based on deviation scores, and (3) a dynamic reward-penalty system for enforcing fair participation. DSFL is evaluated on MNIST, CIFAR-10, and CIFAR-100 under up to 30 percent Byzantine participants in both IID and non-IID settings. It consistently outperforms existing baselines, including LSFL, homomorphic encryption methods, and differential privacy approaches. For example, DSFL achieves 97.15 percent accuracy on CIFAR-10 and 68.60 percent on CIFAR-100, while FedAvg drops to 9.39 percent under similar threats. DSFL remains lightweight, requiring only 55.9 ms runtime and 1088 KB communication per round.

cs.CR↗

arXiv2025

LLM-Enhanced Space-Air-Ground-Sea Integrated Networks

The space-air-ground-sea integrated networking (SAGSIN) concept promises seamless global multimedia connectivity, yet two obstacles still limit its practical deployment. Firstly, high-velocity satellites, aerial relays and sea-surface platforms suffer from obsolete channel state information (CSI), undermining feedback-based adaptation. Secondly, data-rate disparity across the protocol stack is extreme: terabit optical links in space coexist with kilobit acoustic under-water links. This article shows that a single large language model (LLM) backbone, trained jointly on radio, optical and acoustic traces, can provide a unified, data-driven adaptation layer that addresses both rapid CSI ageing and severe bandwidth disparity across the SAGSIN protocol stack. Explicitly, an LLM-based long-range channel predictor forecasts the strongest delay-Doppler components several coherence intervals ahead, facilitating near-capacity reception despite violent channel fluctuations. Furthermore, our LLM-based semantic encoder turns raw sensor payloads into task-oriented tokens. This substantially reduces the SNR required for high-fidelity image delivery in a coastal underwater link, circumventing the data rate limitation by semantic communications. Inclusion of these tools creates a medium-agnostic adaptation layer that spans radio, optical and acoustic channels. We conclude with promising open research directions in on-device model compression, multimodal fidelity control, cross-layer resource orchestration and trustworthy operation, charting a path from laboratory prototypes to field deployment.

eess.SP↗

arXiv2025

Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Due to great success of transformers in many applications such as natural language processing and computer vision, transformers have been successfully applied in automatic modulation classification. We have shown that transformer-based radio signal classification is vulnerable to imperceptible and carefully crafted attacks called adversarial examples. Therefore, we propose a defense system against adversarial examples in transformer-based modulation classifications. Considering the need for computationally efficient architecture particularly for Internet of Things (IoT)-based applications or operation of devices in environment where power supply is limited, we propose a compact transformer for modulation classification. The advantages of robust training such as adversarial training in transformers may not be attainable in compact transformers. By demonstrating this, we propose a novel compact transformer that can enhance robustness in the presence of adversarial attacks. The new method is aimed at transferring the adversarial attention map from the robustly trained large transformer to a compact transformer. The proposed method outperforms the state-of-the-art techniques for the considered white-box scenarios including fast gradient method and projected gradient descent attacks. We have provided reasoning of the underlying working mechanisms and investigated the transferability of the adversarial examples between different architectures. The proposed method has the potential to protect the transformer from the transferability of adversarial examples.

cs.LG↗

arXiv2025

A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification

Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as adversarial examples can significantly deteriorate the performance of the deep learning based radio signal classification. Among various kinds of adversarial examples, universal adversarial perturbation has gained considerable attention due to its feature of being data independent, hence as a practical strategy to fool the radio signal classification with a high success rate. Therefore, in this paper, we investigate a defense system called neural rejection system to propose against universal adversarial perturbations, and evaluate its performance by generating white-box universal adversarial perturbations. We show that the proposed neural rejection system is able to defend universal adversarial perturbations with significantly higher accuracy than the undefended deep neural network.

cs.LG↗

arXiv2025

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications

The remarkable success of transformers across various fields such as natural language processing and computer vision has paved the way for their applications in automatic modulation classification, a critical component in the communication systems of Internet of Things (IoT) devices. However, it has been observed that transformer-based classification of radio signals is susceptible to subtle yet sophisticated adversarial attacks. To address this issue, we have developed a defensive strategy for transformer-based modulation classification systems to counter such adversarial attacks. In this paper, we propose a novel vision transformer (ViT) architecture by introducing a new concept known as adversarial indicator (AdvI) token to detect adversarial attacks. To the best of our knowledge, this is the first work to propose an AdvI token in ViT to defend against adversarial attacks. Integrating an adversarial training method with a detection mechanism using AdvI token, we combine a training time defense and running time defense in a unified neural network model, which reduces architectural complexity of the system compared to detecting adversarial perturbations using separate models. We investigate into the operational principles of our method by examining the attention mechanism. We show the proposed AdvI token acts as a crucial element within the ViT, influencing attention weights and thereby highlighting regions or features in the input data that are potentially suspicious or anomalous. Through experimental results, we demonstrate that our approach surpasses several competitive methods in handling white-box attack scenarios, including those utilizing the fast gradient method, projected gradient descent attacks and basic iterative method.

cs.LG↗

arXiv2025

FAS-LLM: Large Language Model-Based Channel Prediction for OTFS-Enabled Satellite-FAS Links

This paper proposes FAS-LLM, a novel large language model (LLM)-based architecture for predicting future channel states in Orthogonal Time Frequency Space (OTFS)-enabled satellite downlinks equipped with fluid antenna systems (FAS). The proposed method introduces a two-stage channel compression strategy combining reference-port selection and separable principal component analysis (PCA) to extract compact, delay-Doppler-aware representations from high-dimensional OTFS channels. These representations are then embedded into a LoRA-adapted LLM, enabling efficient time-series forecasting of channel coefficients. Performance evaluations demonstrate that FAS-LLM outperforms classical baselines including GRU, LSTM, and Transformer models, achieving up to 10 dB normalized mean squared error (NMSE) improvement and threefold root mean squared error (RMSE) reduction across prediction horizons. Furthermore, the predicted channels preserve key physical-layer characteristics, enabling near-optimal performance in ergodic capacity, spectral efficiency, and outage probability across a wide range of signal-to-noise ratios (SNRs). These results highlight the potential of LLM-based forecasting for delay-sensitive and energy-efficient link adaptation in future satellite IoT networks.

eess.SP↗

arXiv2025

Performance Analysis of Fluid Antenna System Aided OTFS Satellite Communications

Internet-of-Things (IoT) networks typically rely on satellite communications to provide coverage in rural areas. However, high-mobility satellite links introduce severe Doppler and delay spreads, which necessitate the use of orthogonal time frequency space (OTFS) modulation for reliable data transmission. Furthermore, the space and energy constraints on IoT devices make the perfect use case for fluid antenna systems (FAS) due to their mechanical simplicity. Hence, we propose a sophisticated FAS aided OTFS (FAS-OTFS) framework for satellite-based IoT networks. We derive analytical expressions for both the outage probability and ergodic capacity of FAS-OTFS under a general channel model, where the expressions derived are presented in integral form or as analytical bounds for efficient numerical evaluation. Additionally, we investigate a single-path fading scenario, where closed-form expressions are obtained. Our numerical results demonstrate significant performance gains in terms of both the outage probability and capacity compared to conventional OTFS systems, confirming the efficacy of FAS-OTFS in energy-constrained high-mobility environments. Our findings establish FAS-OTFS as a promising candidate for next-generation IoT communications over satellite links.

eess.SP↗

arXiv2025

Reinforcement Learning-Based Downlink Transmit Precoding for Mitigating the Impact of Delayed CSI in Satellite Systems

The integration of low earth orbit (LEO) satellites with terrestrial communication networks holds the promise of seamless global connectivity. The efficiency of this connection, however, depends on the availability of reliable channel state information (CSI). Due to the large space-ground propagation delays, the estimated CSI is outdated. In this paper we consider the downlink of a satellite operating as a base station in support of multiple mobile users. The estimated outdated CSI is used at the satellite side to design a transmit precoding (TPC) matrix for the downlink. We propose a deep reinforcement learning (DRL)-based approach to optimize the TPC matrices, with the goal of maximizing the achievable data rate. We utilize the deep deterministic policy gradient (DDPG) algorithm to handle the continuous action space, and we employ state augmentation techniques to deal with the delayed observations and rewards. We show that the DRL agent is capable of exploiting the time-domain correlations of the channels for constructing accurate TPC matrices. This is because the proposed method is capable of compensating for the effects of delayed CSI in different frequency bands. Furthermore, we study the effect of handovers in the system, and show that the DRL agent is capable of promptly adapting to the environment when a handover occurs.

eess.SP↗

arXiv2025

RIS-Empowered Integrated Location Sensing and Communication with Superimposed Pilots

In addition to enhancing wireless communication coverage quality, reconfigurable intelligent surface (RIS) technique can also assist in positioning. In this work, we consider RIS-assisted superimposed pilot and data transmission without the assumption availability of prior channel state information and position information of mobile user equipments (UEs). To tackle this challenge, we design a frame structure of transmission protocol composed of several location coherence intervals, each with pure-pilot and data-pilot transmission durations. The former is used to estimate UE locations, while the latter is time-slotted, duration of which does not exceed the channel coherence time, where the data and pilot signals are transmitted simultaneously. We conduct the Fisher Information matrix (FIM) analysis and derive \text {Cramér-Rao bound} (CRB) for the position estimation error. The inverse fast Fourier transform (IFFT) is adopted to obtain the estimation results of UE positions, which are then exploited for channel estimation. Furthermore, we derive the closed-form lower bound of the ergodic achievable rate of superimposed pilot (SP) transmission, which is used to optimize the phase profile of the RIS to maximize the achievable sum rate using the genetic algorithm. Finally, numerical results validate the accuracy of the UE position estimation using the IFFT algorithm and the superiority of the proposed SP scheme by comparison with the regular pilot scheme.

cs.IR↗

arXiv2025

A General Sensing-assisted Channel Estimation Framework in Distributed MIMO Network

In 6G communications, it is envisioned to equip the traditional access point (AP) with sensing capability to fully benefit the existing wireless communication infrastructures. Thus, sensing-assisted communication has attracted significant attention from both industry and academia. However, most existing works focused on sensing-assisted communication in line-of-sight (LoS) scenarios due to sensing limitations, where the sensing target (ST) and communication user equipment (UE) remain the same. In this paper, we propose a general sensing-assisted channel estimation framework in the distributed multiple-input and multiple-output (DMIMO) network and consider a scenario where the ST and UE are different entities. In addition, ST is a moving target (e.g. a robot) which causes channels between APs and UEs to vary due to changes in the reflection paths of the indoor environment. Therefore, we let multiple APs to jointly sense the position of the ST, which will be incorporated in a Ray tracing model to obtain a more accurate estimate of the channels from APs to UEs for both the LoS and non-line-of-sight (NLoS) scenarios. Simulation results demonstrate that our proposed sensing-assisted communication framework achieves a much higher channel estimation accuracy and downlink throughput compared to the traditional least-square (LS) channel estimation. More importantly, the feasibility of the proposed framework has been validated to guarantee the stringent channel estimation accuracy requirement in the DMIMO network.

eess.SP↗

arXiv2025

Maximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoning

As we transition from Narrow Artificial Intelligence towards Artificial Super Intelligence, users are increasingly concerned about their privacy and the trustworthiness of machine learning (ML) technology. A common denominator for the metrics of trustworthiness is the quantification of uncertainty inherent in DL algorithms, and specifically in the model parameters, input data, and model predictions. One of the common approaches to address privacy-related issues in DL is to adopt distributed learning such as federated learning (FL), where private raw data is not shared among users. Despite the privacy-preserving mechanisms in FL, it still faces challenges in trustworthiness. Specifically, the malicious users, during training, can systematically create malicious model parameters to compromise the models predictive and generative capabilities, resulting in high uncertainty about their reliability. To demonstrate malicious behaviour, we propose a novel model poisoning attack method named Delphi which aims to maximise the uncertainty of the global model output. We achieve this by taking advantage of the relationship between the uncertainty and the model parameters of the first hidden layer of the local model. Delphi employs two types of optimisation , Bayesian Optimisation and Least Squares Trust Region, to search for the optimal poisoned model parameters, named as Delphi-BO and Delphi-LSTR. We quantify the uncertainty using the KL Divergence to minimise the distance of the predictive probability distribution towards an uncertain distribution of model output. Furthermore, we establish a mathematical proof for the attack effectiveness demonstrated in FL. Numerical results demonstrate that Delphi-BO induces a higher amount of uncertainty than Delphi-LSTR highlighting vulnerability of FL systems to model poisoning attacks.

cs.LG↗

arXiv2024

Enhancing Federated Learning Convergence with Dynamic Data Queue and Data Entropy-driven Participant Selection

Federated Learning (FL) is a decentralized approach for collaborative model training on edge devices. This distributed method of model training offers advantages in privacy, security, regulatory compliance, and cost-efficiency. Our emphasis in this research lies in addressing statistical complexity in FL, especially when the data stored locally across devices is not identically and independently distributed (non-IID). We have observed an accuracy reduction of up to approximately 10\% to 30\%, particularly in skewed scenarios where each edge device trains with only 1 class of data. This reduction is attributed to weight divergence, quantified using the Euclidean distance between device-level class distributions and the population distribution, resulting in a bias term ($δ_k$). As a solution, we present a method to improve convergence in FL by creating a global subset of data on the server and dynamically distributing it across devices using a Dynamic Data queue-driven Federated Learning (DDFL). Next, we leverage Data Entropy metrics to observe the process during each training round and enable reasonable device selection for aggregation. Furthermore, we provide a convergence analysis of our proposed DDFL to justify their viability in practical FL scenarios, aiming for better device selection, a non-sub-optimal global model, and faster convergence. We observe that our approach results in a substantial accuracy boost of approximately 5\% for the MNIST dataset, around 18\% for CIFAR-10, and 20\% for CIFAR-100 with a 10\% global subset of data, outperforming the state-of-the-art (SOTA) aggregation algorithms.

cs.LG↗

arXiv2024

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users

The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared with the centralized server to build the global model. This results in privacy leakage, where the server can infer private information from the shared gradients. To mitigate this flaw, the next-generation FL architectures proposed encryption and anonymization techniques to protect the model updates from the server. However, this approach creates other challenges, such as malicious users sharing false gradients. Since the gradients are encrypted, the server is unable to identify rogue users. To mitigate both attacks, this paper proposes a novel FL algorithm based on a fully homomorphic encryption (FHE) scheme. We develop a distributed multi-key additive homomorphic encryption scheme that supports model aggregation in FL. We also develop a novel aggregation scheme within the encrypted domain, utilizing users' non-poisoning rates, to effectively address data poisoning attacks while ensuring privacy is preserved by the proposed encryption scheme. Rigorous security, privacy, convergence, and experimental analyses have been provided to show that FheFL is novel, secure, and private, and achieves comparable accuracy at reasonable computational cost.

cs.AI↗

arXiv2024

Countermeasures Against Adversarial Examples in Radio Signal Classification

Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial examples. Hence, the reliance of wireless networks on deep learning algorithms poses a serious threat to the security and operation of wireless networks. In this letter, we propose for the first time a countermeasure against adversarial examples in modulation classification. Our countermeasure is based on a neural rejection technique, augmented by label smoothing and Gaussian noise injection, that allows to detect and reject adversarial examples with high accuracy. Our results demonstrate that the proposed countermeasure can protect deep-learning based modulation classification systems against adversarial examples.

cs.AI↗