Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications

The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), such as Gemini-pro, which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data, integrating both textual and visual information on a scale previously unattainable, opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered Gemini-pro LMMs versus fine-tuned Vision Transformer (ViT) models in addressing critical security challenges. We focus on two distinct tasks: a visually evident task of detecting simple triggers, such as small squares in images, indicative of potential backdoors, and a non-visually evident task of malware classification through visual representations. Our results highlight a significant divergence in performance, with Gemini-pro falling short in accuracy and reliability when compared to fine-tuned ViT models. The ViT models, on the other hand, demonstrate exceptional accuracy, achieving near-perfect performance on both tasks. This study not only showcases the strengths and limitations of prompt-engineered LMMs in cybersecurity applications but also emphasizes the unmatched efficacy of fine-tuned ViT models for precise and dependable tasks.

Forecast Analysis of the COVID-19 Incidence in Lebanon: Prediction of Future Epidemiological Trends to Plan More Effective Control Programs

Ever since the COVID-19 pandemic started, all the governments have been trying to limit its effects on their citizens and countries. This pandemic was harsh on different levels for almost all populations worldwide and this is what drove researchers and scientists to get involved and work on several kinds of simulations to get a better insight into this virus and be able to stop it the earliest possible. In this study, we simulate the spread of COVID-19 in Lebanon using an Agent-Based Model where people are modeled as agents that have specific characteristics and behaviors determined from statistical distributions using Monte Carlo Algorithm. These agents can go into the world, interact with each other, and thus, infect each other. This is how the virus spreads. During the simulation, we can introduce different Non-Pharmaceutical Interventions - or more commonly NPIs - that aim to limit the spread of the virus (wearing a mask, closing locations, etc). Our Simulator was first validated on concepts (e.g. Flattening the Curve and Second Wave scenario), and then it was applied on the case of Lebanon. We studied the effect of opening schools and universities on the pandemic situation in the country since the Lebanese Ministry of Education is planning to do so progressively, starting from 21 April 2021. Based on the results we obtained, we conclude that it would be better to delay the school openings while the vaccination campaign is still slow in the country.