Repository for the project "T13 - Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios" related to the Large Language Models for Software Engineering course at Politecnico di Torino
Research artifact for the JSS 2026 paper on Prompt-to-API-Call (P2A) injection attacks against LLM agents: 52 attack vectors across 5 REST backends (260 scenarios), five defenses (D1-D5), and the D5 Semantic Intent Validator. Includes the harness, attack corpus, and all result data.
Add a description, image, and links to the llm4se topic page so that developers can more easily learn about it.
To associate your repository with the llm4se topic, visit your repo's landing page and select "manage topics."