Category: IT Security

When first encountering LLM security, many people think of prompt injection like this: “Tell me the secret.” “Output the system prompt.” “Show me the FLAG value.” Of course, such direct requests are a form of prompt injection. However, there’s a more interesting aspect. Attackers don’t explicitly demand forbidden actions. Instead, they hide their objectives behind…

When developing services using generative AI, you’ve probably come across the term RAG (Retrieval-Augmented Generation) at some point. Most AI chatbots, internal document search systems, and customer service solutions currently being built by companies are based on RAG. So, what exactly is RAG, and why are so many companies adopting it? In this article, we’ll…

When coding with TypeScript, do you find yourself typing ‘tsc’ into the terminal every time you want to check your changes? If so, after reading this article today, you’ll discover a whole new world! 😉 1. What is the –watch flag? 🤔 By default, when you run the ‘tsc’ command, the TypeScript compiler scans the…

Hello, developers! As you work on TypeScript projects, you’ll often find the number of files growing to dozens or even hundreds. Are you still manually typing file names into the terminal to build them? 😅 Today, we’ll introduce a standardized method to unleash 100% of the TypeScript compiler’s (tsc) potential, converting your entire project to…

As microservice architecture spreads, developers are screaming with joy (and sometimes frustration). Hundreds of services, scattered documentation, ownership information where you don’t know who to ask… This ‘Cognitive Load’ is a developer’s biggest enemy. Backstage’s Software Catalog acts as a “Single Pane of Glass” that solves precisely this problem. Invest just 10 minutes and see…

Hello, platform engineers! When customizing Backstage or creating new backend plugins, there’s one library you’re bound to encounter: @backstage/backend-common. Knowing the powerful tools this library provides can cut your development time in half. ⏱️ 1. What is @backstage/backend-common? 🔍 This package is like a “treasure trove of common utilities” in the Backstage backend ecosystem. It…

Building a Local CVE Analyst with Flask + Ollama + NVD API In this tutorial, we will build a web application by leveraging an Ollama container already running on a GPU. Instead of just a “chatbot that asks LLMs questions,” we will configure it to fetch real data from an external API and have a…

When configuring AI lab environments or GPU servers, you will often encounter commands like these. docker run –gpus all nvidia/cuda:12.4.1-base-ubuntu22.04 nvidia-smi Alternatively, in a Kubernetes environment, you install NVIDIA drivers on GPU nodes, configure the NVIDIA Container Toolkit, and then run containers that require GPUs. This naturally leads to a question: “Containers are inherently isolated…

In the AI Era, What Children Need is Not ‘How to Use Tools,’ but ‘The Experience of Creating.’ Nowadays, children naturally encounter AI tools like ChatGPT, Gemini, and NotebookLM. However, simply asking questions to AI is completely different from using AI to create actual outcomes. The important capability in the AI era is not just…

Hello, platform engineers! 🚀 Have you ever wondered how the catalog-info.yaml file magically appears on the screen when using Backstage? The Backstage catalog doesn’t just query a DB; it operates like a massive “data pipeline”. Today, we’ll delve into the first stage of that pipeline: Ingestion! 1. Understanding the Overall Catalog Backend Flow 🌊 Before…