Search

Large Language Models (LLMs) have revolutionised natural language processing tasks, particularly as chat agents. However, their applicability to threat detection problems remains unclear. This paper examines the feasibility of employing LLMs as a Network Intrusion Detection System (NIDS), despite their high computational requirements, primarily for the sake of explainability. Furthermore, considerable resources have been invested in developing LLMs, and they may offer utility for NIDS. Current state-of-the-art NIDS rely on artificial benchmarking datasets, resulting in skewed performance when applied to real-world networking environments. Therefore, we compare the GPT-4 and LLama3 models against traditional architectures and transformer-based models to assess their ability to detect malicious NetFlows without depending on artificially skewed datasets, but solely on their vast pre-trained acquired knowledge. Our results reveal that, although LLMs struggle with precise attack detection, they hold significant potential for a path towards explainable NIDS. Our preliminary exploration shows that LLMs are unfit for the detection of Malicious NetFlows. Most promisingly, however, these exhibit significant potential as complementary agents in NIDS, particularly in providing explanations and aiding in threat response when integrated with Retrieval Augmented Generation (RAG) and function calling capabilities.

A systematic comparison of the models of the circumgalactic medium (CGM) and their observables is crucial to understanding the predictive power of the models and constraining physical processes that affect the thermodynamics of CGM. This paper compares four analytic CGM models: precipitation, isentropic, cooling flow, and baryon pasting models for the hot, volume-filling CGM phase, all assuming hydrostatic or quasi-hydrostatic equilibrium. We show that for fiducial parameters of the CGM of a Milky-Way (MW) like galaxy ($\rm M_{vir} \sim 10^{12}~M_{\odot}$ at $z\sim 0$), the thermodynamic profiles -- entropy, density, temperature, and pressure -- show most significant differences between different models at small ($r\lesssim 30$ kpc) and large scales ($r\gtrsim 100$ kpc) while converging at intermediate scales. The slope of the entropy profile, which is one of the most important differentiators between models, is $\approx 0.8$ for the precipitation and cooling flow models, while it is $\approx0.6$ and 0 for the baryon pasting and isentropic models, respectively. We make predictions for various observational quantities for an MW mass halo for the different models, including the projected Sunyaev-Zeldovich (SZ) effect, soft X-ray emission (0.5--2 keV), dispersion measure, and column densities of oxygen ions (OVI, OVII, and OVIII) observable in absorption., Comment: Comments: 15 pages, 4 figures, 3 tables, accepted for publication in MNRAS

Most diffuse baryons, including the circumgalactic medium (CGM) surrounding galaxies and the intergalactic medium (IGM) in the cosmic web, remain unmeasured and unconstrained. Fast Radio Bursts (FRBs) offer an unparalleled method to measure the electron dispersion measures (DMs) of ionized baryons. Their distribution can resolve the missing baryon problem, and constrain the history of feedback theorized to impart significant energy to the CGM and IGM. We analyze the Cosmology and Astrophysics in Machine Learning (CAMEL) Simulations, using three suites: IllustrisTNG, SIMBA, and Astrid, each varying 6 parameters (2 cosmological & 4 astrophysical feedback), for a total of 183 distinct simulation models. We find significantly different predictions between the fiducial models of the suites, owing to their different implementations of feedback. SIMBA exhibits the strongest feedback, leading to the smoothest distribution of baryons, reducing the sightline-to-sightline variance in DMs between z=0-1. Astrid has the weakest feedback and the largest variance. We calculate FRB CGM measurements as a function of galaxy impact parameter, with SIMBA showing the weakest DMs due to aggressive AGN feedback and Astrid the strongest. Within each suite, the largest differences are due to varying AGN feedback. IllustrisTNG shows the most sensitivity to supernova feedback, but this is due to the change in the AGN feedback strengths, demonstrating that black holes, not stars, are most capable of redistributing baryons in the IGM and CGM. We compare our statistics directly to recent observations, paving the way for the use of FRBs to constrain the physics of galaxy formation and evolution., Comment: 15 pages, 7 figures, Accepted to ApJ

Nonlinearities play a critical role in the dynamics of mechanical resonators, enhancing sensitivity and enabling signal manipulation. Understanding the parameters affecting nonlinearities is crucial for developing strategies to counteract their effects or manipulate them for improved device performance. This study investigates the impact of fabrication-induced curvature on the dynamics of zinc oxide-based piezoelectric micromachined ultrasonic transducers (PMUTs). Our experiments reveal that these devices exhibit hardening, softening, and mixed nonlinear responses, with varying initial static displacements. Notably, PMUTs with almost flat initial static displacement exhibit hardening nonlinearity, while those with a curved initial static displacement show softening nonlinearity. An exotic mixed nonlinear response is observed for intermediate static displacement. We attribute the observed nonlinear response to the interplay between static displacement-induced quadratic nonlinearity and midplane stretching-induced cubic nonlinearity. We provide a theoretical formulation for the dynamics of the devices, which explains the experimental results and highlights the nonlinear responses and their dependence on the initial static displacement. Our findings underscore the significance of nonlinearities in the dynamics of mechanical resonators and suggest ways to optimize device performance., Comment: 19 pages, 7 figures

Working within specific NLP subdomains presents significant challenges, primarily due to a persistent deficit of data. Stringent privacy concerns and limited data accessibility often drive this shortage. Additionally, the medical domain demands high accuracy, where even marginal improvements in model performance can have profound impacts. In this study, we investigate the potential of vocabulary transfer to enhance model performance in biomedical NLP tasks. Specifically, we focus on vocabulary extension, a technique that involves expanding the target vocabulary to incorporate domain-specific biomedical terms. Our findings demonstrate that vocabulary extension, leads to measurable improvements in both downstream model performance and inference time.