arXiv subjects

J. Harshan

Publications and source records attributed to J. Harshan.

At least 19 recordsLinked to original sources

arXiv2026

Robust Berrut-Approximated Coded Computing via Discrete Cosine Transforms

Coded computing is a reliable and fault-tolerant paradigm for executing large-scale computational tasks over distributed worker nodes. Among existing coded computing frameworks, Berrut Approximated Coded Computing (BACC) enables distributed computation of arbitrary non-polynomial functions through rational interpolation. Although BACC provides provable approximation guarantees and resilience against straggling workers, its robustness against Byzantine workers remains largely unexplored. To fill this research gap, we propose Robust Berrut Approximated Coded Computing (RBACC), which establishes a coding-theoretic framework for BACC by enabling error localization and error correction in the presence of Byzantine workers. In particular, RBACC introduces a new choice of evaluation points that establishes a connection between Berrut interpolation and Discrete Cosine Transform (DCT) codes, thereby enabling error localization and error correction under finite-precision arithmetic. We derive analytical upper bounds on the approximation error of RBACC under multiple operating scenarios, including straggler-only systems and systems with Byzantine workers under finite-precision arithmetic. Building upon this analysis, we formulate several optimization problems for selecting the DCT code dimension and for assigning encoded evaluations to unreliable workers. We show that these are previously unexplored design parameters that can be systematically optimized to improve the reconstruction accuracy. Experimental results demonstrate that the proposed RBACC framework effectively mitigates stragglers and Byzantine workers while offering improved reconstruction accuracy over the baselines.

cs.IT↗

arXiv2026

Low-Latency Spatial-Provenance Recovery Methods for Privacy-Constrained Vehicular Networks

In multihop Vehicle-to-Everything (V2X) networks, Road Side Units (RSUs) intend to collect information on vehicles' location in a low-latency manner while respecting their privacy constraints to support real-time location-based services. To facilitate data collection, provenance is known to ensure trust and accountability of data. Although existing joint data- and spatial-provenance techniques preserve the privacy of vehicles up to a certain granularity with respect to the RSU and other vehicles, they are unsuitable when stringent deadlines are imposed on the end-to-end delay on the packets. As a consequence, there is a need for designing spatial-provenance methods for V2X networks that satisfy stringent deadlines on the end-to-end delays while managing the privacy concerns. To fill this research gap, we propose two novel protocols, namely: Bi-Segment Embedding (BSE) and Tri-Segment Embedding (TSE), which provide a skipping mechanism for joint data- and spatial-provenance while trading off privacy features among the vehicles. Through an extensive theoretical framework, we provide an analysis of the proposed schemes in terms of reliability, privacy, and communication overhead. When compared to the baselines, our protocols offer lower end-to-end delay, higher reliability in provenance reconstruction, and the same level of privacy with respect to the RSU. We validate latency gains using practical radio parameters, and our study reveals that our proposed protocols offer significant benefits in latency when implemented over a 5G stack.

cs.NI↗

arXiv2026

Cooperative Mitigation against Learning-Based Reactive Jammers: Analysis and SDR Validation

Motivated by recent developments in full-duplex radios, cognitive radios, and data-driven signal-processing, we propose a novel class of reactive jamming adversaries wherein the adversary transmits jamming energy on the victim's frequency band while simultaneously monitoring various energy statistics in the network to detect the presence of potential countermeasures, thereby trapping the victim. These adversaries employ generalized energy detectors comprising statistical detectors, based on instantaneous and distributional energy metrics, and data-driven detectors employing machine-learning classifiers to learn patterns in the observed energy sequences. Against such a strong adversary, we propose a family of cooperative mitigation strategies wherein the victim takes assistance from a helper node, with the strategies tailored to operate under a wide range of latency requirements on victim's messages and practical radio hardware constraints at helper node. To provide theoretical guarantees on their efficacy, interesting optimization problems are formulated on the choice of their underlying parameters, followed by extensive mathematical analyses on their error performance and covertness. To assess their practical feasibility, we implement the before-deployment and after-deployment setups on a software-defined-radio-based hardware testbed, and to evaluate their detectability on real energy observations, we collect the corresponding datasets to train and test the data-driven machine-learning classifiers employed by adversary. Both analytical and hardware evaluations show that the proposed strategies cannot be detected with a high-probability under the generalized energy detectors used by adversary.

cs.IT↗

arXiv2026

Balancing Privacy and Robustness in Coded Computing Under Profiled Workers

In distributed computing with untrusted workers, the assignment of evaluation indices plays a critical role in determining both privacy and robustness. In this work, we study how the placement of unreliable workers within the Numerically Stable Lagrange Coded Computing (NS-LCC) framework influences privacy and the ability to localize Byzantine errors. We derive analytical bounds that quantify how different evaluation-index assignments affect privacy against colluding curious workers and robustness against Byzantine corruption under finite-precision arithmetic. Using these bounds, we formulate optimization problems that identify privacy-optimal and robustness-optimal index placements and show that the resulting assignments are fundamentally different. This exposes that index choices that maximizes privacy degrade error-localization, and vice versa. To jointly navigate this trade-off, we propose a low-complexity greedy assignment strategy that closely approximates the optimal balance between privacy and robustness.

cs.IT↗

arXiv2026

Basis-Spline Assisted Coded Computing: Strategies and Error Bounds

Coded computing has emerged as a key framework for addressing the impact of stragglers in distributed computation. While polynomial functions often admit exact recovery under existing coded computing schemes, non-polynomial functions require approximate reconstruction from a finite number of evaluations, posing significant challenges. Consequently, interpolation-based methods for non-polynomial coded computing have gained attention, with Berrut approximated coded computing emerging as a state-of-the-art approach. However, due to the global support of Berrut interpolants, the reconstruction accuracy degrades significantly as the number of stragglers increases. To address this challenge, we propose a coded computing framework based on cubic B-spline interpolation. In our approach, server-side function evaluations are reconstructed at the master using B-splines, exploiting their local support and smoothness properties to enhance stability and accuracy. We provide a systematic methodology for integrating B-spline interpolation into coded computing and derive theoretical bounds on approximation error for certain class of smooth functions. Our analysis demonstrates that the error bounds of our approach exhibit a faster decay with respect to the number of workers compared to the Berrut-based method. Experimental results also confirm that our method offers improved accuracy over Berrut-based methods for various smooth non-polynomial functions.

cs.IT↗

arXiv2025

Robust Analog Lagrange Coded Computing: Theory and Algorithms via Discrete Fourier Transforms

Analog Lagrange Coded Computing (ALCC) is a recently proposed computational paradigm wherein certain computations over analog datasets are efficiently performed using distributed worker nodes through floating point representation. While the vanilla version of ALCC is known to preserve the privacy of the datasets from the workers and also achieve resilience against stragglers, it is not robust against Byzantine workers that return erroneous results. Highlighting this vulnerability, we propose a Robust ALCC framework that is resilient against a wide range of integrity threats from the Byzantine workers. As a foundational step, we use error-correction algorithms for Discrete Fourier Transform (DFT) codes to build novel reconstruction strategies for ALCC thereby improving its computational accuracy in the presence of a bounded number of Byzantine workers. Furthermore, capitalizing on some theoretical results on the performance of the DFT decoders, we propose novel strategies for distributing the ALCC computational tasks to the workers, and show that such methods significantly improve the accuracy when the workers' trust profiles are available at the master server. Finally, we study the robustness of the proposed framework against colluding attacks, and show that interesting attack strategies can be executed by exploiting the inherent precision noise owing to floating point implementation.

cs.IT↗

arXiv2025

On Spatial-Provenance Recovery in Wireless Networks with Relaxed-Privacy Constraints

In Vehicle-to-Everything (V2X) networks with multi-hop communication, Road Side Units (RSUs) intend to gather location data from the vehicles to offer various location-based services. Although vehicles use the Global Positioning System (GPS) for navigation, they may refrain from sharing their exact GPS coordinates to the RSUs due to privacy considerations. Thus, to address the localization expectations of the RSUs and the privacy concerns of the vehicles, we introduce a relaxed-privacy model wherein the vehicles share their partial location information in order to avail the location-based services. To implement this notion of relaxed-privacy, we propose a low-latency protocol for spatial-provenance recovery, wherein vehicles use correlated linear Bloom filters to embed their position information. Our proposed spatial-provenance recovery process takes into account the resolution of localization, the underlying ad hoc protocol, and the coverage range of the wireless technology used by the vehicles. Through a rigorous theoretical analysis, we present extensive analysis on the underlying trade-off between relaxed-privacy and the communication-overhead of the protocol. Finally, using a wireless testbed, we show that our proposed method requires a few bits in the packet header to provide security features such as localizing a low-power jammer executing a denial-of-service attack.

cs.CR↗

arXiv2025

FORTA: Byzantine-Resilient FL Aggregation via DFT-Guided Krum

Secure federated learning enables collaborative model training across decentralized users while preserving data privacy. A key component is secure aggregation, which keeps individual updates hidden from both the server and users, while also defending against Byzantine users who corrupt the aggregation. To this end, Jinhyun So et al. recently developed a Byzantine-resilient secure aggregation scheme using a secret-sharing strategy over finite-field arithmetic. However, such an approach can suffer from numerical errors and overflows when applied to real-valued model updates, motivating the need for secure aggregation methods that operate directly over the real domain. We propose FORTA, a Byzantine-resilient secure aggregation framework that operates entirely in the real domain. FORTA leverages Discrete Fourier Transform (DFT) codes for privacy and employs Krum-based outlier detection for robustness. While DFT decoder is error-free under infinite precision, finite precision introduces numerical perturbations that can distort distance estimates and allow malicious updates to evade detection. To address this, FORTA refines Krum using feedback from DFT decoder, improving the selection of trustworthy updates. Theoretical analysis and experiments show that our modification of Krum offers improved robustness and more accurate aggregation than standard Krum.

cs.CR↗

arXiv2025

On Securing Berrut Approximated Coded Computing Through Discrete Cosine Transforms

Coded computing is a reliable and fault-tolerant mechanism for implementing large computing tasks over a distributed set of worker nodes. While a majority of coded computing frameworks address accurate computation of the target functions, they are restricted to computing multivariate polynomial functions. To generalize these computing platforms to non-polynomial target functions, Jahani-Nezhad and Maddah-Ali recently proposed Berrut Approximated Coded computing (BACC), which was proven fault-tolerant against stragglers albiet with tolerable approximation errors on the target functions. Despite these benefits, there is no formal study on the security of BACC against worker nodes which report erroneous computations. To fill this research gap, we use a coding-theoretic approach to propose Secure Berrut Approximated Coded Computing (SBACC), which is resilient to stragglers and also robust to the presence of such untrusted worker nodes. One of the highlights of SBACC is the new choice of evaluation points for distributed computation which makes the well-known Discrete Cosine Transform (DCT) codes amenable to error detection and correction. To validate the new choice of evaluation points, first, we derive bounds on the accuracy of SBACC in the absence of untrusted worker nodes. Subsequently, to handle the presence of untrusted worker nodes, we derive bounds on the accuracy of SBACC and show that interesting optimization problems can be formulated to study the trade-off between the error correcting capability of the DCT codes and the accuracy of the target computation.

cs.IT↗

arXiv2025

Network-Centric Countermeasures Against Integrated Sensing Enabled Jamming Adversaries

Recent developments in Integrated Sensing and Communication have led to new adversarial models in wireless security through Integrated Sensing and Jamming (ISAJ) adversaries. ISAJ adversaries, owing to their sensing capabilities, are known to inject jamming energy over the victim's frequency band, and also use generalized energy measurements on various network frequencies to detect the presence of countermeasures. Existing countermeasures against such ISAJ adversaries are laid under the assumption that the adversary does not have the knowledge of the countermeasure. However, according to Kerchoffs' principle in cryptography, security of a countermeasure should only rely on the secret-keys, not on the obfuscation of the countermeasure. On testing the security of existing countermeasures, we observe that they violate Kerchoffs' principle, thus motivating the need for new countermeasures. In this regard, we propose a novel network-centric countermeasure against ISAJ adversaries, wherein a group of users in the network assist the victim to reliably communicate her messages in a covert manner. Firstly, we analyse the error performance of the proposed countermeasure, and study its behavior on the number of assisting users in the network. Subsequently, to validate its security against Kerchoffs' principle, we study the Shannon's entropy associated with the presence of the victim's messages in the network and analyse its behaviour as a function of the number of assisting users. Finally, to study the interplay between reliability and covertness, we pose interesting optimization problems and solve them to choose the underlying parameters of the countermeasure and the number of assisting users.

cs.IT↗

arXiv2025

Helper-Friendly Latency-Bounded Mitigation Strategies against Reactive Jamming Adversaries

Due to the recent developments in the field of full-duplex radios and cognitive radios, a new class of reactive jamming attacks has gained attention wherein an adversary transmits jamming energy over the victim's frequency band and also monitors various energy statistics in the network so as to detect countermeasures, thereby trapping the victim. Although cooperative mitigation strategies against such security threats exist, they are known to incur spectral-efficiency loss on the helper node, and are also not robust to variable latency-constraints on victim's messages. Identifying these research gaps in existing countermeasures against reactive jamming attacks, we propose a family of helper-friendly cooperative mitigation strategies that are applicable for a wide-range of latency-requirements on the victim's messages as well as practical radio hardware at the helper nodes. The proposed strategies are designed to facilitate reliable communication for the victim, without compromising the helper's spectral efficiency and also minimally disturbing the various energy statistics in the network. For theoretical guarantees on their efficacy, interesting optimization problems are formulated on the choice of the underlying parameters, followed by extensive mathematical analyses on their error-performance and covertness. Experimental results indicate that the proposed strategies should be preferred over the state-of-the-art methods when the helper node is unwilling to compromise on its error performance for assisting the victim.

cs.IT↗

arXiv2024

On Homomorphic Encryption Based Strategies for Class Imbalance in Federated Learning

Class imbalance in training datasets can lead to bias and poor generalization in machine learning models. While pre-processing of training datasets can efficiently address both these issues in centralized learning environments, it is challenging to detect and address these issues in a distributed learning environment such as federated learning. In this paper, we propose FLICKER, a privacy preserving framework to address issues related to global class imbalance in federated learning. At the heart of our contribution lies the popular CKKS homomorphic encryption scheme, which is used by the clients to privately share their data attributes, and subsequently balance their datasets before implementing the FL scheme. Extensive experimental results show that our proposed method significantly improves the FL accuracy numbers when used along with popular datasets and relevant baselines.

cs.CR↗

arXiv2024

On Securing Analog Lagrange Coded Computing from Colluding Adversaries

Analog Lagrange Coded Computing (ALCC) is a recently proposed coded computing paradigm wherein certain computations over analog datasets can be efficiently performed using distributed worker nodes through floating point implementation. While ALCC is known to preserve privacy of data from the workers, it is not resilient to adversarial workers that return erroneous computation results. Pointing at this security vulnerability, we focus on securing ALCC from a wide range of non-colluding and colluding adversarial workers. As a foundational step, we make use of error-correction algorithms for Discrete Fourier Transform (DFT) codes to build novel algorithms to nullify the erroneous computations returned from the adversaries. Furthermore, when such a robust ALCC is implemented in practical settings, we show that the presence of precision errors in the system can be exploited by the adversaries to propose novel colluding attacks to degrade the computation accuracy. As the main takeaway, we prove a counter-intuitive result that not all the adversaries should inject noise in their computations in order to optimally degrade the accuracy of the ALCC framework. This is the first work of its kind to address the vulnerability of ALCC against colluding adversaries.

cs.IT↗

arXiv2024

On Scaling LT-Coded Blockchains in Heterogeneous Networks and their Vulnerabilities to DoS Threats

Coded blockchains have acquired prominence as a promising solution to reduce storage costs and facilitate scalability. Within this class, Luby Transform (LT) coded blockchains are an appealing choice for scalability owing to the availability of a wide range of low-complexity decoders. In the first part of this work, we identify that traditional LT decoders like Belief Propagation and On-the-Fly Gaussian Elimination may not be optimal for heterogeneous networks with nodes that have varying computational and download capabilities. To address this, we introduce a family of hybrid decoders for LT codes and propose optimal operating regimes for them to recover the blockchain at the lowest decoding cost. While LT coded blockchain architecture has been studied from the aspects of storage savings and scalability, not much is known in terms of its security vulnerabilities. Pointing at this research gap, in the second part, we present novel denial-of-service threats on LT coded blockchains that target nodes with specific decoding capabilities, preventing them from joining the network. Our proposed threats are non-oblivious in nature, wherein adversaries gain access to the archived blocks, and choose to execute their attack on a subset of them based on underlying coding scheme. We show that our optimized threats can achieve the same level of damage as that of blind attacks, however, with limited amount of resources. Overall, this is the first work of its kind that opens up new questions on designing coded blockchains to jointly provide storage savings, scalability and also resilience to optimized threats.

cs.IT↗

arXiv2024

On Learning Spatial Provenance in Privacy-Constrained Wireless Networks

In Vehicle-to-Everything networks that involve multi-hop communication, the Road Side Units (RSUs) typically aim to collect location information from the participating vehicles to provide security and network diagnostics features. While the vehicles commonly use the Global Positioning System (GPS) for navigation, they may refrain from sharing their precise GPS coordinates with the RSUs due to privacy concerns. Therefore, to jointly address the high localization requirements by the RSUs as well as the vehicles' privacy, we present a novel spatial-provenance framework wherein each vehicle uses Bloom filters to embed their partial location information when forwarding the packets. In this framework, the RSUs and the vehicles agree upon fragmenting the coverage area into several smaller regions so that the vehicles can embed the identity of their regions through Bloom filters. Given the probabilistic nature of Bloom filters, we derive an analytical expression on the error-rates in provenance recovery and then pose an optimization problem to choose the underlying parameters. With the help of extensive simulation results, we show that our method offers near-optimal Bloom filter parameters in learning spatial provenance. Some interesting trade-offs between the communication-overhead, spatial privacy of the vehicles and the error rates in provenance recovery are also discussed.

cs.IT↗

arXiv2024

A Prototype on the Feasibility of Learning Spatial Provenance in XBee and LoRa Networks

In Vehicle-to-Everything (V2X) networks that involve multi-hop communication, the Road Side Units (RSUs) typically desire to gather the location information of the participating vehicles to provide security and network-diagnostics features. Although Global Positioning System (GPS) based localization is widely used by vehicles for navigation; they may not forward their exact GPS coordinates to the RSUs due to privacy issues. Therefore, to balance the high-localization requirements of RSU and the privacy of the vehicles, we demonstrate a new spatial-provenance framework wherein the vehicles agree to compromise their privacy to a certain extent and share a low-precision variant of its coordinates in agreement with the demands of the RSU. To study the deployment feasibility of the proposed framework in state-of-the-art wireless standards, we propose a testbed of ZigBee and LoRa devices and implement the underlying protocols on their stack using correlated Bloom filters and Rake compression algorithms. Our demonstrations reveal that low-to-moderate precision localization can be achieved in fewer packets, thus making an appealing case for next-generation vehicular networks to include our methods for providing real-time security and network-diagnostics features.

cs.NI↗

arXiv2023

Seeing is Believing: A Federated Learning Based Prototype to Detect Wireless Injection Attacks

Reactive injection attacks are a class of security threats in wireless networks wherein adversaries opportunistically inject spoofing packets in the frequency band of a client thereby forcing the base-station to deploy impersonation-detection methods. Towards circumventing such threats, we implement secret-key based physical-layer signalling methods at the clients which allow the base-stations to deploy machine learning (ML) models on their in-phase and quadrature samples at the baseband for attack detection. Using Adalm Pluto based software defined radios to implement the secret-key based signalling methods, we show that robust ML models can be designed at the base-stations. However, we also point out that, in practice, insufficient availability of training datasets at the base-stations can make these methods ineffective. Thus, we use a federated learning framework in the backhaul network, wherein a group of base-stations that need to protect their clients against reactive injection threats collaborate to refine their ML models by ensuring privacy on their datasets. Using a network of XBee devices to implement the backhaul network, experimental results on our federated learning setup shows significant enhancements in the detection accuracy, thus presenting wireless security as an excellent use-case for federated learning in 6G networks and beyond.

cs.IT↗

arXiv2023

Self-Sustainable Key Generation: Strategies and Performance Bounds under DoS Attacks

Denial-of-Service (DoS) threats pose a major challenge to the idea of physical-layer key generation as the underlying wireless channels for key extraction are usually public. Identifying this vulnerability, we study the effect of DoS threats on relay-assisted key generation, and show that a reactive jamming attack on the distribution phase of relay-assisted key generation can forbid the nodes from extracting secret keys. To circumvent this problem, we propose a self-sustainable key generation model, wherein a frequency-hopping based distribution phase is employed to evade the jamming attack even though the participating nodes do not share prior credentials. A salient feature of the idea is to carve out a few bits from the key generation phase and subsequently use them to pick a frequency band at random for the broadcast phase. Interesting resource-allocation problems are formulated on how to extract maximum number of secret bits while also being able to evade the jamming attack with high probability. Tractable low-complexity solutions are also provided to the resource-allocation problems, along with insights on the feasibility of their implementation in practice.

cs.IT↗