marktechpost

A Coding Implementation to Establish Rigorous Prompt Versioning and Regression Testing Workflows for Large Language Models using MLflow

In this tutorial, we show how we treat prompts as first-class, versioned artifacts and apply rigorous regression testing to large language model behavior using MLflow. We design an evaluation pipeline ...
GitHub

Intelligent Modular System for Translating Natural Language Queries (NLQs) into SQL using LLMs

Natural Language to SQL system developed as a final degree project (TFG) graded 10/10, and proposed for honors. The system translates user queries written in natural language into SQL, executes them ...
IEEE

DaMiT-SQL: Detecting and Mitigating Text-to-SQL Prompt Injection Attacks

Abstract: Large Language Models (LLMs) are known for their ability to understand and respond to human instructions/prompts. As such, LLMs can be used to produce natural language interfaces for ...
IEEE

Semantic-Augmented Prompt-Guided Sketch Filling for Text-to-SQL Generation

Abstract: Querying relational databases through natural language remains a difficult task, especially for users without knowledge of SQL. Existing Text-to-SQL approaches often face issues of semantic ...
Microsoft

A one-prompt attack that breaks LLM safety alignment

Large language models (LLMs) and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety ...
GitHub

Cisco AI Agent Skills Security Scanner

A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and ...