Software and Security Engineer
LLM Security: A Scientific Taxonomy of Attack Vectors
Introduction Security in Large Language Models (LLMs) is no longer a small topic inside NLP (Natural Language Processing). It has become its own field within computer security. Between 2021 and 2025, research moved from studying adversarial examples in classifiers to looking at bigger risks: alignment, memorization, context contamination, and models that keep behaving in harmful ways. The problem today is not only a bug in the code. It comes from how the system is built: the architecture, the training data, the alignment methods, and how the model is connected to other systems. ...
How a Large Language Model (LLM) Works
1. Fundamental Architecture: The Transformer The foundation of modern LLMs (Large Language Models) is the Transformer architecture [1]. Unlike RNNs (Recurrent Neural Networks) and LSTMs (Long Short-Term Memory networks), which process text one step after another, the Transformer processes the entire sequence in parallel. This allows better modeling of long-range dependencies and faster training [1]. Figure: Flow of the Transformer architecture (attention, encoder/decoder, feed-forward). Source: Vaswani et al. [1]. ...
ArgusScan: Automating Ethical Pentest with Shodan API
Introduction Security professionals know that reconnaissance is one of the most important steps in a penetration test. Finding vulnerable systems, understanding network exposure, and identifying potential attack surfaces takes time and requires using multiple tools. What if you could automate this process while maintaining professional standards and generating reports that follow industry methodologies like PTES and OWASP? That’s where ArgusScan comes in. It’s an open-source Python CLI tool that integrates with Shodan API to automate ethical pentest reconnaissance, making security assessments faster and more efficient. ...
Monitoring Lab: A Complete Observability Lab with Go, Spring Boot and Prometheus
Introduction Observability is essential for understanding how applications perform in production. When you can see what your systems are doing, you can make better decisions about performance, resource usage, and reliability. I built a Monitoring Lab to compare how Go and Spring Boot applications perform under similar conditions. Both applications connect to MongoDB and perform the same operations, while Prometheus collects metrics and Grafana visualizes the results. This article focuses on the actual results and what the metrics tell us about the performance differences between these two technologies. ...