arXiv subjects

S. S. Iyengar

Publications and source records attributed to S. S. Iyengar.

9 recordsLinked to original sources

arXiv2026

Quantum-Enhanced Distributed Sensor Fusion: Lower Bounds on Aggregation from Projection Noise to Heisenberg-Limited Byzantine-Tolerant Networks

We derive unified lower bounds on the mean squared error (MSE) of distributed quantum sensor fusion under Byzantine faults and decoherence. Building on the classical Brooks-Iyengar overlap function and its vector extension, the predictive outlier model for virtual sensor tracking, and SPOTLESS spatial-temporal verification, we establish a two-parameter family of bounds indexed by entanglement visibility V and fault fraction f/M. For M quantum sensors with N atoms each and sensitivity eta, the MSE of any estimator satisfies MSE >= (1-V^2)/(4*N*eta^2*M_eff) + V^2/(4*N*eta^2*M_eff^2), where M_eff = M-2f under Brooks-Iyengar Byzantine fault tolerance and M_eff = M-f when predictive outlier detection successfully identifies faulty sensors. The bound interpolates continuously between the standard quantum limit (V=0, scaling as 1/sqrt(M_eff)) and the Heisenberg limit (V=1, scaling as 1/M_eff). Monte Carlo simulations with up to 64 sensors validate the theoretical scaling laws. Validation on the Intel Berkeley Lab 54-mote dataset with spatial clustering demonstrates 20-27 dB SNR improvement from entanglement per cluster, and reveals that missing classical sensor data degrades fusion agreement in the same pattern as quantum decoherence. The framework bridges quantum metrology with classical stream-processing architectures including Data-Cleaning Trees and the 80-20 Power Law for scale-invariant clustering.

cs.DC↗

arXiv2026

CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation

Large Language Models (LLMs) such as Gemma-2B have shown strong performance in various natural language processing tasks. However, general-purpose models often lack the domain expertise required for cybersecurity applications. This work presents a methodology to fine-tune the Gemma-2B model into a domain-specific cybersecurity LLM. We detail the processes of dataset preparation, fine-tuning, and synthetic data generation, along with implications for real-world applications in threat detection, forensic investigation, and attack analysis. Experiments highlight challenges in prompt length distribution during domain-specific fine-tuning. Uneven prompt lengths limit the model's effective use of the context window, constraining local inference to 200-400 tokens despite hardware support for longer sequences. Chain-of-thought styled prompts, paired with quantized weights, yielded the best performance under these constraints. To address context limitations, we employed a hybrid strategy using cloud LLMs for synthetic data generation and local fine-tuning for deployment efficiency. To extend the evaluation, we introduce a Retrieval-Augmented Generation (RAG) pipeline and graph-based reasoning framework. This approach enables structured alignment with MITRE ATT&CK techniques through STIX-based threat intelligence, enhancing recall in multi-hop and long-context scenarios. Graph modules encode entity-neighborhood context and tactic chains, helping mitigate the constraints of short prompt windows. Results demonstrate improved model alignment with tactic, technique, and procedure (TTP) coverage, validating the utility of graph-augmented LLMs in cybersecurity threat intelligence applications.

cs.CR↗

arXiv2025

Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions

Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as text. LMs have a wide range of applications in natural language processing (NLP) tasks, including autocomplete and machine translation. Although larger datasets typically enhance LM performance, scalability remains a challenge due to constraints in computational power and resources. Distributed computing strategies offer essential solutions for improving scalability and managing the growing computational demand. Further, the use of sensitive datasets in training and deployment raises significant privacy concerns. Recent research has focused on developing decentralized techniques to enable distributed training and inference while utilizing diverse computational resources and enabling edge AI. This paper presents a survey on distributed solutions for various LMs, including large language models (LLMs), vision language models (VLMs), multimodal LLMs (MLLMs), and small language models (SLMs). While LLMs focus on processing and generating text, MLLMs are designed to handle multiple modalities of data (e.g., text, images, and audio) and to integrate them for broader applications. To this end, this paper reviews key advancements across the MLLM pipeline, including distributed training, inference, fine-tuning, and deployment, while also identifying the contributions, limitations, and future areas of improvement. Further, it categorizes the literature based on six primary focus areas of decentralization. Our analysis describes gaps in current methodologies for enabling distributed solutions for LMs and outline future research directions, emphasizing the need for novel solutions to enhance the robustness and applicability of distributed LMs.

cs.CL↗

arXiv2019

Insights from BB-MAS -- A Large Dataset for Typing, Gait and Swipes of the Same Person on Desktop, Tablet and Phone

Behavioral biometrics are key components in the landscape of research in continuous and active user authentication. However, there is a lack of large datasets with multiple activities, such as typing, gait and swipe performed by the same person. Furthermore, large datasets with multiple activities performed on multiple devices by the same person are non-existent. The difficulties of procuring devices, participants, designing protocol, secure storage and on-field hindrances may have contributed to this scarcity. The availability of such a dataset is crucial to forward the research in behavioral biometrics as usage of multiple devices by a person is common nowadays. Through this paper, we share our dataset, the details of its collection, features for each modality and our findings of how keystroke features vary across devices. We have collected data from 117 subjects for typing (both fixed and free text), gait (walking, upstairs and downstairs) and touch on Desktop, Tablet and Phone. The dataset consists a total of about: 3.5 million keystroke events; 57.1 million data-points for accelerometer and gyroscope each; 1.7 million data-points for swipes; and enables future research to explore previously unexplored directions in inter-device and inter-modality biometrics. Our analysis on keystrokes reveals that in most cases, keyhold times are smaller but inter-key latencies are larger, on hand-held devices when compared to desktop. We also present; detailed comparison with related datasets; possible research directions with the dataset; and lessons learnt from the data collection.

cs.HC↗

arXiv2016

Sparsity-Based Error Detection in DC Power Flow State Estimation

This paper presents a new approach for identifying the measurement error in the DC power flow state estimation problem. The proposed algorithm exploits the singularity of the impedance matrix and the sparsity of the error vector by posing the DC power flow problem as a sparse vector recovery problem that leverages the structure of the power system and uses $l_1$-norm minimization for state estimation. This approach can provably compute the measurement errors exactly, and its performance is robust to the arbitrary magnitudes of the measurement errors. Hence, the proposed approach can detect the noisy elements if the measurements are contaminated with additive white Gaussian noise plus sparse noise with large magnitude. The effectiveness of the proposed sparsity-based decomposition-DC power flow approach is demonstrated on the IEEE 118-bus and 300-bus test systems.

cs.IT↗

arXiv2015

Optimal Two-Tier Forecasting Power Generation Model in Smart Grids

There has been an increasing trend in the electric power system from a centralized generation-driven grid to a more reliable, environmental friendly, and customer-driven grid. One of the most important issues which the designers of smart grids need to deal with is to forecast the fluctuations of power demand and generation in order to make the power system facilities more flexible to the variable nature of renewable power resources and demand-side. This paper proposes a novel two-tier scheme for forecasting the power demand and generation in a general residential electrical gird which uses the distributed renewable resources as the primary energy resource. The proposed forecasting scheme has two tiers: long-term demand/generation forecaster which is based on Maximum-Likelihood Estimator (MLE) and real-time demand/generation forecaster which is based on Auto-Regressive Integrated Moving-Average (ARIMA) model. The paper also shows that how bulk generation improves the adequacy of proposed residential system by canceling-out the forecasters estimation errors which are in the form of Gaussian White noises.

eess.SY↗

arXiv2013

Forecasting Stock Time-Series using Data Approximation and Pattern Sequence Similarity

Time series analysis is the process of building a model using statistical techniques to represent characteristics of time series data. Processing and forecasting huge time series data is a challenging task. This paper presents Approximation and Prediction of Stock Time-series data (APST), which is a two step approach to predict the direction of change of stock price indices. First, performs data approximation by using the technique called Multilevel Segment Mean (MSM). In second phase, prediction is performed for the approximated data using Euclidian distance and Nearest-Neighbour technique. The computational cost of data approximation is O(n ni) and computational cost of prediction task is O(m |NN|). Thus, the accuracy and the time required for prediction in the proposed method is comparatively efficient than the existing Label Based Forecasting (LBF) method [1].

cs.DB↗

arXiv2010

Oblivious Buy-at-Bulk in Planar Graphs

In the oblivious buy-at-bulk network design problem in a graph, the task is to compute a fixed set of paths for every pair of source-destinations in the graph, such that any set of demands can be routed along these paths. The demands could be aggregated at intermediate edges where the fusion-cost is specified by a canonical (non-negative concave) function $f$. We give a novel algorithm for planar graphs which is oblivious with respect to the demands, and is also oblivious with respect to the fusion function $f$. The algorithm is deterministic and computes the fixed set of paths in polynomial time, and guarantees a $O(\log n)$ approximation ratio for any set of demands and any canonical fusion function $f$, where $n$ is the number of nodes. The algorithm is asymptotically optimal, since it is known that this problem cannot be approximated with better than $Ω(\log n)$ ratio. To our knowledge, this is the first tight analysis for planar graphs, and improves the approximation ratio by a factor of $\log n$ with respect to previously known results.

cs.DS↗

arXiv2010

An Oblivious Spanning Tree for Buy-at-Bulk Network Design Problems

We consider the problem of constructing a single spanning tree for the single-source buy-at-bulk network design problem for doubling-dimension graphs. We compute a spanning tree to route a set of demands (or data) along a graph to or from a designated root node. The demands could be aggregated at (or symmetrically distributed to) intermediate nodes where the fusion-cost is specified by a non-negative concave function $f$. We describe a novel approach for developing an oblivious spanning tree in the sense that it is independent of the number of data sources (or demands) and cost function at intermediate nodes. To our knowledge, this is the first paper to propose a single spanning tree solution to this problem (as opposed to multiple overlay trees). There has been no prior work where the tree is oblivious to both the fusion cost function and the set of sources (demands). We present a deterministic, polynomial-time algorithm for constructing a spanning tree in low doubling graphs that guarantees $\log^{3}D\cdot\log n$-approximation over the optimal cost, where $D$ is the diameter of the graph and $n$ the total number of nodes. With constant fusion-cost function our spanning tree gives a $O(\log^3 D)$-approximation for every Steiner tree to the root.

cs.DS↗