arXiv subjects

Harshil Patel

Publications and source records attributed to Harshil Patel.

8 recordsLinked to original sources

arXiv2026

Generative AI for Encrypted Traffic Analysis: Synthetic Dataset Generation and Classifier Evaluation

Network traffic analysis faces significant challenges with encrypted communications, primarily due to limited visibility into packet contents and the inherent imbalance in available datasets, particularly for anomalous traffic patterns. This paper addresses these challenges by exploring Generative AI (GAI) techniques to create realistic and balanced synthetic encrypted traffic datasets. Our approach incorporates feature analysis, clustering-based data generation, and comprehensive classifier evaluation to ensure synthetic data quality. We demonstrate that properly generated synthetic data can effectively supplement real- world datasets, achieving up to 93% performance when training classifiers compared to those trained on real data. The proposed methodology preserves critical statistical properties and feature correlations while enabling the creation of balanced datasets, ad- dressing the persistent challenge of anomaly underrepresentation in cybersecurity data. Along with the results we provide complete programming code designed and implemented in this work.

cs.CR↗

arXiv2026

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop. We hypothesize that tool error messages possess implicit authority, triggering corrective reasoning modes that bypass standard safety heuristics. We introduce VATS (Vulnerability Analysis of Tool Streams), a mutation-driven framework that systematically evolves adversarial payloads across seven structural and linguistic dimensions. Our evaluation across four frontier models, Gemini 3.1 Pro, GPT-5.5, GLM-5.1, and Qwen3-Coder, demonstrates that error-path injection triples the success rate of standard indirect prompt injection (IPI), achieving up to 100% compliance in controlled evaluations. We isolate structural positioning (sandwiching instructions within error context) as the most effective exploit vector across all tested models. While we find that production framework guardrails can mitigate these vulnerabilities, the inherent susceptibility of the model layer poses a systemic risk to bespoke agentic workflows.

cs.AI↗

arXiv2026

NAAMSE: Framework for Evolutionary Security Evaluation of Agents

AI agents are increasingly deployed in production, yet their security evaluations remain bottlenecked by manual red-teaming or static benchmarks that fail to model adaptive, multi-turn adversaries. We propose NAAMSE, an evolutionary framework that reframes agent security evaluation as a feedback-driven optimization problem. Our system employs a single autonomous agent that orchestrates a lifecycle of genetic prompt mutation, hierarchical corpus exploration, and asymmetric behavioral scoring. By using model responses as a fitness signal, the framework iteratively compounds effective attack strategies while simultaneously ensuring "benign-use correctness", preventing the degenerate security of blanket refusal. Our experiments across a diverse suite of state-of-the-art large language models demonstrate that evolutionary mutation systematically amplifies vulnerabilities missed by one-shot methods, with controlled ablations revealing that the synergy between exploration and targeted mutation uncovers high-severity failure modes. We show that this adaptive approach provides a more realistic and scalable assessment of agent robustness in the face of evolving threats. The code for NAAMSE is open source and available at https://github.com/HASHIRU-AI/NAAMSE.

cs.AI↗

arXiv2025

Toward Reproducible and Standardized Computer Architecture Simulation with gem5

Reproducibility in simulation-based computer architecture research requires coordinating artifacts like disk images, kernels, and benchmarks, but existing workflows are inconsistent. We improve gem5, an open-source simulator with over 1600 forks, and gem5 Resources, a centralized repository of over 2000 pre-packaged artifacts, to address these issues. While gem5 Resources enables artifact sharing, researchers still face challenges. Creating custom disk images is complex and time-consuming, with no standardized process across ISAs, making it difficult to extend and share images. gem5 provides limited guest-host communication features through a set of predefined exit events that restrict researchers' ability to dynamically control and monitor simulations. Lastly, running simulations with multiple workloads requires researchers to write custom external scripts to coordinate multiple gem5 simulations which creates error-prone and hard-to-reproduce workflows. To overcome this, we introduce several features in gem5 and gem5 Resources. We standardize disk-image creation across x86, ARM, and RISC-V using Packer, and provide validated base images with pre-annotated benchmark suites (NPB, GAPBS). We provide 12 new disk images, 6 new kernels, and over 200 workloads across three ISAs. We refactor the exit event system to a class-based model and introduce hypercalls for enhanced guest-host communication that allows researchers to define custom behavior for their exit events. We also provide a utility to remotely monitor simulations and the gem5-bridge driver for user-space m5 operations. Additionally, we implemented Suites and MultiSim to enable parallel full-system simulations from gem5 configuration scripts, eliminating the need for external scripting. These features reduce setup complexity and provide extensible, validated resources that improve reproducibility and standardization.

cs.AR↗

arXiv2025

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization

Rapid Large Language Model (LLM) advancements are fueling autonomous Multi-Agent System (MAS) development. However, current frameworks often lack flexibility, resource awareness, model diversity, and autonomous tool creation. This paper introduces HASHIRU (Hierarchical Agent System for Hybrid Intelligent Resource Utilization), a novel MAS framework enhancing flexibility, resource efficiency, and adaptability. HASHIRU features a "CEO" agent dynamically managing specialized "employee" agents, instantiated based on task needs and resource constraints (cost, memory). Its hybrid intelligence prioritizes smaller, local LLMs (via Ollama) while flexibly using external APIs and larger models when necessary. An economic model with hiring/firing costs promotes team stability and efficient resource allocation. The system also includes autonomous API tool creation and a memory function. Evaluations on tasks like academic paper review (58% success), safety assessments (100% on a JailbreakBench subset), and complex reasoning (outperforming Gemini 2.0 Flash on GSM8K: 96% vs. 61%; JEEBench: 80% vs. 68.3%; SVAMP: 92% vs. 84%) demonstrate HASHIRU's capabilities. Case studies illustrate its self-improvement via autonomous cost model generation, tool integration, and budget management. HASHIRU offers a promising approach for more robust, efficient, and adaptable MAS through dynamic hierarchical control, resource-aware hybrid intelligence, and autonomous functional extension. Source code and benchmarks are available at https://github.com/HASHIRU-AI/HASHIRU and https://github.com/HASHIRU-AI/HASHIRUBench respectively, and a live demo is available at https://hashiruagentx-hashiruai.hf.space upon request.

cs.MA↗

arXiv2024

Physics-informed neural networks need a physicist to be accurate: the case of mass and heat transport in Fischer-Tropsch catalyst particles

Physics-Informed Neural Networks (PINNs) have emerged as an influential technology, merging the swift and automated capabilities of machine learning with the precision and dependability of simulations grounded in theoretical physics. PINNs are often employed to solve algebraic or differential equations to replace some or even all steps of multi-stage computational workflows, leading to their significant speed-up. However, wide adoption of PINNs is still hindered by reliability issues, particularly at extreme ends of the input parameter ranges. In this study, we demonstrate this in the context of a system of coupled non-linear differential reaction-diffusion and heat transfer equations related to Fischer-Tropsch synthesis, which are solved by a finite-difference method with a PINN used in evaluating their source terms. It is shown that the testing strategies traditionally used to assess the accuracy of neural networks as function approximators can overlook the peculiarities which ultimately cause instabilities of the finite-difference solver. We propose a domain knowledge-based modifications to the PINN architecture ensuring its correct asymptotic behavior. When combined with an improved numerical scheme employed as an initial guess generator, the proposed modifications are shown to recover the overall stability of the simulations, while preserving the speed-up brought by PINN as the workflow component. We discuss the possible applications of the proposed hybrid transport equation solver in context of chemical reactors simulations.

cs.LG↗

arXiv2024

Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, prompting interest in their application as black-box optimizers. This paper asserts that LLMs possess the capability for zero-shot optimization across diverse scenarios, including multi-objective and high-dimensional problems. We introduce a novel population-based method for numerical optimization using LLMs called Language-Model-Based Evolutionary Optimizer (LEO). Our hypothesis is supported through numerical examples, spanning benchmark and industrial engineering problems such as supersonic nozzle shape optimization, heat transfer, and windfarm layout optimization. We compare our method to several gradient-based and gradient-free optimization approaches. While LLMs yield comparable results to state-of-the-art methods, their imaginative nature and propensity to hallucinate demand careful handling. We provide practical guidelines for obtaining reliable answers from LLMs and discuss method limitations and potential research directions.

cs.AI↗

arXiv2023

Accurate and Fast Fischer-Tropsch Reaction Microkinetics using PINNs

Microkinetics allows detailed modelling of chemical transformations occurring in many industrially relevant reactions. Traditional way of solving the microkinetics model for Fischer-Tropsch synthesis (FTS) becomes inefficient when it comes to more advanced real-time applications. In this work, we address these challenges by using physics-informed neural networks(PINNs) for modelling FTS microkinetics. We propose a computationally efficient and accurate method, enabling the ultra-fast solution of the existing microkinetics models in realistic process conditions. The proposed PINN model computes the fraction of vacant catalytic sites, a key quantity in FTS microkinetics, with median relative error (MRE) of 0.03%, and the FTS product formation rates with MRE of 0.1%. Compared to conventional equation solvers, the model achieves up to 1E+06 times speed-up when running on GPUs, thus being fast enough for multi-scale and multi-physics reactor modelling and enabling its applications in real-time process control and optimization.

cs.LG↗