arXiv subjects

Dhananjay Thiruvady

Publications and source records attributed to Dhananjay Thiruvady.

At least 19 recordsLinked to original sources

arXiv2026

Audio Physical Dynamics Inspired Deepfake Detection for Voice Authentication Systems

Voice authentication systems deployed at the network edge face dual threats: a) sophisticated deepfake synthesis attacks and b) control-plane poisoning in distributed federated learning protocols. We present a framework coupling audio physical dynamics deepfake detection with uncertainty-aware in edge learning. The framework fuses interpretable physics features modeling vocal tract dynamics with representations coming from a self-supervised learning module. The representations are then processed via a streamlined Multi-Layer Perceptron backbone, followed by a Bayesian ensemble providing uncertainty estimates. Incorporating audio physical characteristics evaluations and uncertainty estimates of audio samples allows our proposed framework to remain robust to advanced deepfake attacks, while our trust-based aggregation protocol secures the control plane against poisoning in network edge voice authentication systems.

cs.SD↗

arXiv2026

Overcoming Tight Constraints in Soft Happy Colouring

The Soft Happy Colouring (SHC) problem, a mathematical framework for identifying homophilic network structures, seeks to maximise the number of $ρ$-happy vertices, i.e., vertices with at least a proportion $ρ$ of neighbours that share the same colour. Because this NP-hard problem makes finding exact solutions intractable for large networks, probabilistic metaheuristics such as the Cross-Entropy (CE) method are suitable candidates. However, pure CE frequently suffers from stagnation of the probability distributions and non-convergence in high-dimensional spaces. To address this, we introduce {\sf CE+LS}, synergising CE's adaptive learning with a fast, structure-aware local search ({\sf LS}). By restricting the search exclusively to local optima, {\sf CE+LS} learns from high-quality structural characteristics rather than raw random samples. We mathematically and empirically demonstrate that this search space reduction resolves CE's stagnation, yielding a convergent algorithm. Evaluating {\sf CE+LS} across 28,000 Stochastic Block Model graphs, validated by non-parametric statistical testing, demonstrates that it consistently outperforms existing heuristic and memetic algorithms. Furthermore, benchmarking against the commercial exact solver, CPLEX, on real-world networks confirms that {\sf CE+LS} identifies near-optimal configurations in a fraction of the required computational time for CPLEX. Crucially, {\sf CE+LS} remains highly efficient even in the tight constraint regime, where comparative algorithms usually fail.

cs.SI↗

arXiv2026

Multiobjective Model Predictive Control for Residential Demand Response Management Under Uncertainty

Residential users in demand response programs must balance electricity costs and user dissatisfaction under real-time pricing. This study proposes a multiobjective model predictive control approach for home energy management systems with battery storage, aiming to minimize both objectives while mitigating uncertainties. Laguerre functions parameterize control signals, transforming the optimization problem into one with linear inequalities for efficient exploration. A constrained multiobjective evolutionary algorithm, incorporating convex sampler-based crossover and mutation, is developed to ensure feasible solutions. Simulations show that the proposed method outperforms existing approaches, limiting cost increases to 0.52\% under uncertainties, compared to at least 2.3\% with other methods.

eess.SY↗

arXiv2026

ALFA: A Safe-by-Design Approach to Mitigate Quishing Attacks Launched via Fancy QR Codes

Phishing with Quick Response (QR) codes is termed as Quishing. The attackers exploit this method to manipulate individuals into revealing their confidential data. Recently, we see the colorful and fancy representations of QR codes, the 2D matrix of QR codes which does not reflect a typical mixture of black-white modules anymore. Instead, they become more tempting as an attack vector for adversaries which can evade the state-of-the-art deep learning visual-based and other prevailing countermeasures. We introduce "ALFA", a safe-by-design approach, to mitigate Quishing and prevent everyone from accessing the post-scan harmful payload of fancy QR codes. Our method first converts a fancy QR code into the replica of binary grid and then identify the erroneous representation of modules in that grid. Following that, we present "FAST" method which can conveniently recover erroneous modules from that binary grid. Afterwards, using this binary grid, our solution extracts the structural features of fancy QR code and predicts its legitimacy using a pre-trained model. The effectiveness of our proposal is demonstrated by the experimental evaluation on a synthetic dataset (containing diverse variations of fancy QR codes) and achieve a FNR of 0.06% only. We also develop the mobile app to test the practical feasibility of our solution and provide a performance comparison of the app with the real-world QR readers. This comparison further highlights the classification reliability and detection accuracy of this solution in real-world environments.

cs.CR↗

arXiv2025

Finding happiness by evolutionary algorithms

A recent line of research concerns the problem of soft happy colouring (SHC), which requires that a partially coloured graph be extended to a complete colouring to maximise local agreements, so that as many vertices as possible end up surrounded by enough same-coloured neighbours. It is already known that SHC is NP-hard, and its solutions have a direct relationship with the community structure of networks; thus, it has immense applications in security and resilience. Past studies have shown that local search approaches can be fast and effective to an extent on the SHC; however, they often get stuck in local optima. Regarding the related problem of maximising happy vertices, evolutionary approaches have been proven effective; hence, this study develops a customised memetic algorithm that is a hybrid of genetic algorithms and local search. The experimental evaluation on a range of graphs in the stochastic block model shows that the memetic algorithm can achieve excellent results in search for an optimised solution to SHC compared to the local search approaches and standard genetic algorithms. Moreover, learning and evolution in the memetic algorithm allow diversification of solutions generated by fast, effective local search approaches, which prove superior for the challenging problem of community detection.

cs.DM↗

arXiv2025

Bayesian Network Fusion of Large Language Models for Sentiment Analysis

Large language models (LLMs) continue to advance, with an increasing number of domain-specific variants tailored for specialised tasks. However, these models often lack transparency and explainability, can be costly to fine-tune, require substantial prompt engineering, yield inconsistent results across domains, and impose significant adverse environmental impact due to their high computational demands. To address these challenges, we propose the Bayesian network LLM fusion (BNLF) framework, which integrates predictions from three LLMs, including FinBERT, RoBERTa, and BERTweet, through a probabilistic mechanism for sentiment analysis. BNLF performs late fusion by modelling the sentiment predictions from multiple LLMs as probabilistic nodes within a Bayesian network. Evaluated across three human-annotated financial corpora with distinct linguistic and contextual characteristics, BNLF demonstrates consistent gains of about six percent in accuracy over the baseline LLMs, underscoring its robustness to dataset variability and the effectiveness of probabilistic fusion for interpretable sentiment classification.

cs.CL↗

arXiv2025

Causal Modelling of Cryptocurrency Price Movements Using Discretisation-Aware Bayesian Networks

This study identifies the key factors influencing the price movements of major cryptocurrencies, Bitcoin, Binance Coin, Ethereum, Litecoin, Ripple, and Tether, using Bayesian networks (BNs). This study addresses two key challenges: modelling price movements in highly volatile cryptocurrency markets and enhancing predictive performance through discretisation-aware Bayesian Networks. It analyses both macro-financial indicators (gold, oil, MSCI, S and P 500, USDX) and social media signals (tweet volume) as potential price drivers. Moreover, since discretisation is a critical step in the effectiveness of BNs, we implement a structured procedure to build 54 BNs models by combining three discretisation methods (equal interval, equal quantile, and k-means) with several bin counts. These models are evaluated using four metrics, including balanced accuracy, F1 score, area under the ROC curve and a composite score. Results show that equal interval with two bins consistently yields the best predictive performance. We also provide deeper insights into each network's structure through inference, sensitivity, and influence strength analyses. These analyses reveal distinct price-driving patterns for each cryptocurrency, underscore the importance of coin-specific analysis, and demonstrate the value of BNs for interpretable causal modelling in volatile cryptocurrency markets.

q-fin.ST↗

arXiv2025

A Bi-Objective Mathematical Model for the Multi-Skilled Resource-Constrained Project Scheduling Problem Considering Reliability: An AUGMECON2VIKOR Hybrid Method

In recent years, resources with multiple skills have received attention as an extension of the resource-constrained project scheduling problem known as MSRCPSP. Although the disruption rate is well-estimated in today's manufacturing projects, its impact on project makespan and cost need further investigation. Hence, this study presents a novel mathematical model for the MSRCPSP considering reliability, namely MSRCPSPR. The model proposes both objectives of minimizing project makespan and project cost. The MSRCPSP is an NP-hard problem, and including reliability constraints, as proposed in this paper, makes solving the problem more intractable. To cope with the computational challenges of solving the problem, a combination of an enhanced version of the epsilon-constraint method as well as an augmented version of the VIKOR algorithm, namely AUGMECON2VIKOR, is employed to solve benchmark instances j10 and j20 from the PSPLIB. A comparative analysis demonstrates the performance of the proposed method, and the sensitivity analysis represents the effects of positive reliable constraints on the objective functions. Employing the proposed method, the project makespan and cost are reduced by nearly 2.55% and 2.80% in j10 on average. CPU time is also decreased by about 543 seconds in comparison to the epsilon-constraint method.

math.OC↗

arXiv2025

Local Search Improvements for Soft Happy Colouring

For $0\leq ρ\leq 1$ and a coloured graph $G$, a vertex $v$ is $ρ$-happy if at least $ρ\mathrm{deg}(v)$ of its neighbours have the same colour as $v$. Soft happy colouring of a partially coloured graph $G$ is the problem of finding a vertex colouring $σ$ that preserves the precolouring and has the maximum number of $ρ$-happy vertices. It is already known that this problem is NP-hard and directly relates to the community structure of the graphs; under a certain condition on the proportion of happiness $ρ$ and for graphs with community structures, the induced colouring by communities can make all the vertices $ρ$-happy. We show that when $0\leq ρ_1<ρ_2\leq 1$, a complete $ρ_2$-happy colouring has a higher accuracy of community detection than a complete $ρ_1$-happy colouring. Moreover, when $ρ$ is greater than a threshold, it is unlikely for an algorithm to find a complete $ρ$-happy colouring with colour classes of almost equal sizes. Three local search algorithms for soft happy colouring are proposed, and their performances are compared with one another and other known algorithms. Among them, the linear-time local search is shown to be not only very fast, but also a reliable algorithm that can dramatically improve the number of $ρ$-happy vertices.

cs.DM↗

arXiv2025

Mitigating Backdoor Triggered and Targeted Data Poisoning Attacks in Voice Authentication Systems

Voice authentication systems remain susceptible to two major threats: backdoor triggered attacks and targeted data poisoning attacks. This dual vulnerability is critical because conventional solutions typically address each threat type separately, leaving systems exposed to adversaries who can exploit both attacks simultaneously. We propose a unified defense framework that effectively addresses both BTA and TDPA. Our framework integrates a frequency focused detection mechanism that flags covert pitch boosting and sound masking backdoor attacks in near real time, followed by a convolutional neural network that addresses TDPA. This dual layered defense approach utilizes multidimensional acoustic features to isolate anomalous signals without requiring costly model retraining. In particular, our PBSM detection mechanism can seamlessly integrate into existing voice authentication pipelines and scale effectively for large scale deployments. Experimental results on benchmark datasets and their compression with the state of the art algorithm demonstrate that our PBSM detection mechanism outperforms the state of the art. Our framework reduces attack success rates to as low as five to fifteen percent while maintaining a recall rate of up to ninety five percent in recognizing TDPA.

cs.CR↗

arXiv2024

Soft happy colourings and community structure of networks

For $0<ρ\leq 1$, a $ρ$-happy vertex $v$ in a coloured graph $G$ has at least $ρ\cdot \mathrm{deg}(v)$ same-colour neighbours, and a $ρ$-happy colouring (aka soft happy colouring) of $G$ is a vertex colouring that makes all the vertices $ρ$-happy. A community is a subgraph whose vertices are more adjacent to themselves than the rest of the vertices. Graphs with community structures can be modelled by random graph models such as the stochastic block model (SBM). In this paper, we present several theorems showing that both of these notions are related, with numerous real-world applications. We show that, with high probability, communities of graphs in the stochastic block model induce $ρ$-happy colouring on all vertices if certain conditions on the model parameters are satisfied. Moreover, a probabilistic threshold on $ρ$ is derived so that communities of a graph in the SBM induce a $ρ$-happy colouring. Furthermore, the asymptotic behaviour of $ρ$-happy colouring induced by the graph's communities is discussed when $ρ$ is less than a threshold. We develop heuristic polynomial-time algorithms for soft happy colouring that often correlate with the graphs' community structure. Finally, we present an experimental evaluation to compare the performance of the proposed algorithms thereby demonstrating the validity of the theoretical results.

cs.DM↗

arXiv2024

Dynamic Bayesian Networks for Predicting Cryptocurrency Price Directions: Uncovering Causal Relationships

Cryptocurrencies have gained popularity across various sectors, especially in finance and investment. Despite their growing popularity, cryptocurrencies can be a high-risk investment due to their price volatility. The inherent volatility in cryptocurrency prices, coupled with the effects of external global economic factors, makes predicting their price movements challenging. To address this challenge, we propose a dynamic Bayesian network (DBN)-based approach to uncover potential causal relationships among various features including social media data, traditional financial market factors, and technical indicators. Six popular cryptocurrencies, Bitcoin, Binance Coin, Ethereum, Litecoin, Ripple, and Tether are studied in this work. The proposed model's performance is compared to five baseline models of auto-regressive integrated moving average, support vector regression, long short-term memory, random forests, and support vector machines. The results show that while DBN performance varies across cryptocurrencies, with some cryptocurrencies exhibiting higher predictive accuracy than others, the DBN significantly outperforms the baseline models.

cs.LG↗

arXiv2024

Securing Voice Authentication Applications Against Targeted Data Poisoning

Deep neural network-based voice authentication systems are promising biometric verification techniques that uniquely identify biological characteristics to verify a user. However, they are particularly susceptible to targeted data poisoning attacks, where attackers replace legitimate users' utterances with their own. We propose an enhanced framework using realworld datasets considering realistic attack scenarios. The results show that the proposed approach is robust, providing accurate authentications even when only a small fraction (5% of the dataset) is poisoned.

cs.CR↗

arXiv2024

A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading

Despite advances in artificial intelligence-enhanced trading methods, developing a profitable automated trading system remains challenging in the rapidly evolving cryptocurrency market. This research focuses on developing a reinforcement learning (RL) framework to tackle the complexities of trading five prominent altcoins: Binance Coin, Ethereum, Litecoin, Ripple, and Tether. To this end, we present the CausalReinforceNet~(CRN) framework, which integrates both Bayesian and dynamic Bayesian network techniques to empower the RL agent in trade decision-making. We develop two agents using the framework based on distinct RL algorithms to analyse performance compared to the Buy-and-Hold benchmark strategy and a baseline RL model. The results indicate that our framework surpasses both models in profitability, highlighting CRN's consistent superiority, although the level of effectiveness varies across different cryptocurrencies.

cs.AI↗

arXiv2024

Fruit Classification System with Deep Learning and Neural Architecture Search

The fruit identification process involves analyzing and categorizing different types of fruits based on their visual characteristics. This activity can be achieved using a range of methodologies, encompassing manual examination, conventional computer vision methodologies, and more sophisticated methodologies employing machine learning and deep learning. Our study identified a total of 15 distinct categories of fruit, consisting of class Avocado, Banana, Cherry, Apple Braeburn, Apple golden 1, Apricot, Grape, Kiwi, Mango, Orange, Papaya, Peach, Pineapple, Pomegranate and Strawberry. Neural Architecture Search (NAS) is a technological advancement employed within the realm of deep learning and artificial intelligence, to automate conceptualizing and refining neural network topologies. NAS aims to identify neural network structures that are highly suitable for tasks, such as the detection of fruits. Our suggested model with 99.98% mAP increased the detection performance of the preceding research study that used Fruit datasets. In addition, after the completion of the study, a comparative analysis was carried out to assess the findings in conjunction with those of another research that is connected to the topic. When compared to the findings of earlier studies, the detector that was proposed exhibited higher performance in terms of both its accuracy and its precision.

cs.CV↗

arXiv2024

Risk-Constrained Community Battery Utilisation Optimisation for Electric Vehicle Charging with Photovoltaic Resources

High penetration of renewable generation in the electricity grid presents power system operators with challenges including voltage instability mainly due to fluctuating power generation. To cope with intermittent generation, community batteries introduce an elegant solution for storing excess generation of renewable resources and reverting to the grid in peak demand periods. The question of the right battery type and size coupled with the right investment is challenging. Furthermore, the growth in adapting EVs imposes additional demand challenges on the power system compared to traditional industrial and household demand. This paper introduces long-term planning for community batteries to capture the surplus generation of PV resources for a given area and redirect these resources to charge EVs, without direct injection to the grid. For long-term investment planning on batteries, we consider 15 years' worth of historical data associated with solar irradiance, temperature, EV demands, and household demands. A novel stochastic mathematical model is proposed for decision-making on battery specifications (the type and capacity per year) based on the four standard battery types provided by the CSIRO in Australia. Uncertainties related to the EVs and RESs are captured by a non-parametric robust technique, named information gap decision theory, from optimistic and pessimistic perspectives. The investment decision-making part is formulated as mixed-integer linear programming taking advantage of the powerful commercial solver -- GUROBI -- which leads to finding feasible global solutions with low computational burden. The outcomes of this investigation not only detect optimal battery installation strategies to improve the stability profile of the grid by capturing the excess generation of PV resources but also facilitate EV integration in the community toward reaching net-zero emissions targets.

math.OC↗

arXiv2024

Genetic-based Constraint Programming for Resource Constrained Job Scheduling

Resource constrained job scheduling is a hard combinatorial optimisation problem that originates in the mining industry. Off-the-shelf solvers cannot solve this problem satisfactorily in reasonable timeframes, while other solution methods such as many evolutionary computation methods and matheuristics cannot guarantee optimality and require low-level customisation and specialised heuristics to be effective. This paper addresses this gap by proposing a genetic programming algorithm to discover efficient search strategies of constraint programming for resource-constrained job scheduling. In the proposed algorithm, evolved programs represent variable selectors to be used in the search process of constraint programming, and their fitness is determined by the quality of solutions obtained for training instances. The novelties of this algorithm are (1) a new representation of variable selectors, (2) a new fitness evaluation scheme, and (3) a pre-selection mechanism. Tests with a large set of random and benchmark instances, the evolved variable selectors can significantly improve the efficiency of constraining programming. Compared to highly customised metaheuristics and hybrid algorithms, evolved variable selectors can help constraint programming identify quality solutions faster and proving optimality is possible if sufficiently large run-times are allowed. The evolved variable selectors are especially helpful when solving instances with large numbers of machines.

cs.NE↗

arXiv2023

Enhancing Constraint Programming via Supervised Learning for Job Shop Scheduling

Constraint programming (CP) is a powerful technique for solving constraint satisfaction and optimization problems. In CP solvers, the variable ordering strategy used to select which variable to explore first in the solving process has a significant impact on solver effectiveness. To address this issue, we propose a novel variable ordering strategy based on supervised learning, which we evaluate in the context of job shop scheduling problems. Our learning-based methods predict the optimal solution of a problem instance and use the predicted solution to order variables for CP solvers. \added[]{Unlike traditional variable ordering methods, our methods can learn from the characteristics of each problem instance and customize the variable ordering strategy accordingly, leading to improved solver performance.} Our experiments demonstrate that training machine learning models is highly efficient and can achieve high accuracy. Furthermore, our learned variable ordering methods perform competitively when compared to four existing methods. Finally, we demonstrate that hybridising the machine learning-based variable ordering methods with traditional domain-based methods is beneficial.

cs.AI↗