arXiv subjects

Mayank Raj

Publications and source records attributed to Mayank Raj.

6 recordsLinked to original sources

arXiv2026

Synthetic Network Packet Generation through Statistical Learning and Genetic Algorithms

Developing robust intrusion detection systems (IDS) for IoT environments requires large, labeled datasets capturing realistic traffic distributions across both benign and malicious activity. Existing public datasets suffer from fixed activity distributions and extreme class imbalance, while deep generative models (GANs, VAEs) provide no mechanism to enforce that synthetic packets remain within physically valid feature ranges. This paper proposes and compares two constraint-enforcing approaches for synthetic IoT network packet generation: (i) a statistical learning method combining PCA-based latent space sampling with dual One-Class SVM (OCSVM) and Isolation Forest (IF) boundary enforcement, and (ii) a genetic algorithm (GA) method that treats packet generation as a multi-objective optimization problem with explicit fitness criteria for anomaly model acceptance and distributional fidelity. Both methods embed hard validity constraints -- dual anomaly-detection gating, feature-range clamping, and independent validation -- directly into the synthesis pipeline. Evaluation on the complete ACI IoT 2023 dataset (1,231,411 packets, 12 attack categories, class imbalance up to 175,805:1) demonstrates that both methods achieve PASS status across all categories under independently trained validators with a 30% anomaly rate threshold: the statistical method attains 1.20% average anomaly rate with ~1,091 packets/s throughput, while the GA attains 0.62% average anomaly rate with organic per-class variance (0.00%-2.50%) at ~5.7 packets/s. Both methods successfully amplify the 5-sample ARP Spoofing category by 200x to 1,000 validated packets. The ~190:1 throughput ratio between methods, combined with their complementary quality profiles, provides evidence-based selection criteria for deployment contexts ranging from rapid dataset augmentation to adversarial robustness testing.

cs.CR↗

arXiv2026

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks. These attacks add carefully crafted perturbations to network traffic data that leads to misclassifications. While prior work has demonstrated adversarial vulnerabilities in isolated settings, systematic cross-architecture as well as class and category of attack based comparisons under controlled attack conditions remain limited, leaving practitioners without clear guidance on which models to deploy in adversarial environments. This paper asks a simple question: what type of classifier architectures actually hold up when attackers try to manipulate the systems? We put three popular architectures through their paces: a 1D Convolutional Neural Network, a Long Short-Term Memory (LSTM) network, and a Random Forest (RF) ensemble. Using the ACI-IoT-2023 dataset (over 1.2 million samples spanning 12 attack types), we subject each model with FGSM and PGD adversarial attacks, which apply gradient-based perturbations in normalized feature space consistent with established adversarial ML evaluation protocols, at perturbation budgets ranging from $\epsilon=0.01$ to $\epsilon=0.1$. Surprisingly, Random Forest achieved near-perfect baseline accuracy (99.98\%), yet collapsed catastrophically under attack, dropping 73 percentage points at the smallest perturbation we tested. CNN, on the other hand, retained 95.5\% accuracy at $\epsilon=0.01$ and degraded gracefully as perturbations increased. LSTM fell somewhere in between. These findings flip the conventional wisdom where high baseline accuracy means nothing if a model shatters at the first sign of adversarial pressure. For practitioners deploying intrusion detection in adversarial environments, we recommend CNN-based architectures and provide scenario-specific deployment guidance.

cs.CR↗

arXiv2026

A Neural-Network Framework to Learn History-Dependent Constitutive Laws and Identifiability of Internal Variables

The identification of constitutive laws is ubiquitous in engineering: in modeling of materials where experimental data are fitted to mathematical models or learning surrogate models to beat the FE\textsuperscript{2} computational cost of multiscale numerical simulations. However, these models of constitutive laws, unless equipped with a potential formulation, are not necessarily consistent with (a) the second law of thermodynamics; (b) stability of the material under extreme applied strain; and (c) the mathematical theory underpinning the existence of solutions of the governing equation. In this work, we present a causal and energetic formulation, consistent with aforementioned properties, of learning a history-dependent constitutive law. This characterization of the class of internal variables sheds light on the equivalence class of equivalent surrogate models for the constitutive law. We show that the internal variables that are learned from the data are unique up to a linear transform. The framework is deployed to learn the Taylor-averaged response of a polycrystalline magnesium unit cell. We achieve 2\% relative error in the prediction of the Taylor-averaged response.

cond-mat.mtrl-sci↗

arXiv2025

Effective behavior of heterogeneous media governed by strain gradient elasticity

Various mechanical phenomena depend on the length scale, and these have inspired a variety of nonlocal and higher gradient continuum theories. Mechanistically, it is believed that the length scale dependence arises due to an interplay between the length scale of heterogeneities in the material, the length scale of the material being probed and the phenomenon under study. In this paper, we seek to understand this interplay in a simple setting by studying the overall behavior of a one-dimensional periodic medium governed by strain gradient elasticity at the microstructural scale. We find through numerical experiments that the overall behavior is not described by a strain gradient elasticity. In other words, strain gradient theories are not invariant under averaging at this scale. We also find that the overall behavior may be described by a kernel-based nonlocal elasticity theory, but the kernel is highly oscillatory with slow decay. So we seek alternate characterization. First, we limit our interest to a range of length scales, and show that the behavior is described well by fractional strain gradient elasticity. Consequently, one can obtain various scaling laws with exponent between zero (classical elasticity) and one (strain-gradient elasticity). Second, we take a data-driven approach, and show that we can describe the overall behavior over a range of scales using a Fourier neural operator.

cond-mat.mtrl-sci↗

arXiv2022

Physics-informed neural networks for solving thermo-mechanics problems of functionally graded material

Differential equations are indispensable to engineering and hence to innovation. In recent years, physics-informed neural networks (PINN) have emerged as a novel method for solving differential equations. PINN method has the advantage of being meshless, scalable, and can potentially be intelligent in terms of transferring the knowledge learned from solving one differential equation to the other. The exploration in this field has majorly been limited to solving linear-elasticity problems, crack propagation problems. This study uses PINNs to solve coupled thermo-mechanics problems of materials with functionally graded properties. An in-depth analysis of the PINN framework has been carried out by understanding the training datasets, model architecture, and loss functions. The efficacy of the PINN models in solving thermo-mechanics differential equations has been measured by comparing the obtained solutions either with analytical solutions or finite element method-based solutions. While R2 score of more than 99% has been achieved in predicting primary variables such as displacement and temperature fields, achieving the same for secondary variables such as stress turns out to be more challenging. This study is the first to implement the PINN framework for solving coupled thermo-mechanics problems on composite materials. This study is expected to enhance the understanding of the novel PINN framework and will be seminal for further research on PINNs.

cs.CE↗

arXiv2020

Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles

This paper describes our system (Solomon) details and results of participation in the SemEval 2020 Task 11 "Detection of Propaganda Techniques in News Articles"\cite{DaSanMartinoSemeval20task11}. We participated in Task "Technique Classification" (TC) which is a multi-class classification task. To address the TC task, we used RoBERTa based transformer architecture for fine-tuning on the propaganda dataset. The predictions of RoBERTa were further fine-tuned by class-dependent-minority-class classifiers. A special classifier, which employs dynamically adapted Least Common Sub-sequence algorithm, is used to adapt to the intricacies of repetition class. Compared to the other participating systems, our submission is ranked 4th on the leaderboard.

cs.CL↗