Artigos
Escrevo principalmente sobre segurança, sistemas distribuídos e inteligência artificial. Os textos em inglês permanecem no original.
grep --topic
- [AI Security]
· · 9 minDistillation Attack on LLMs (Model Extraction via Knowledge Distillation)In normal machine learning, knowledge distillation is a training method. A large "teacher" model teaches a smaller "student" model. The student learns to copy the teacher's outputs. This makes the student faster and chea - [AI Security]
· · 9 minLLM Security: A Scientific Taxonomy of Attack VectorsA technical overview of how LLM security research evolved from adversarial examples to systemic risks: jailbreaks, prompt injection, memorization, backdoors, and supply chain issues. - [Software]
· · 12 minHow a Large Language Model (LLM) WorksA clear overview of how LLMs work: Transformer architecture, data processing, training, alignment (SFT, RLHF, RLAIF), and efficiency techniques like MoE, RAG, and FlashAttention. - [Security]
· · 12 minArgusScan: Automating Ethical Pentest with Shodan APIIntroducing ArgusScan, an open-source Python CLI tool that automates ethical pentest reconnaissance using Shodan API, with professional reporting and 96% test coverage. - [Software]
· · 12 minMonitoring Lab: A Complete Observability Lab with Go, Spring Boot and PrometheusA performance comparison between Go and Spring Boot applications using real metrics from Prometheus and Grafana dashboards.