Global ETD Search

In the Shadow of Prompts: Adversarial Attacks and Model Cloning in Large Language Models

Gharami, Kanchon

<p>Large-language models (LLMs) already power mission critical tasks such as command-and-control chat, satellite ground-station automation, military analytics, and cyber-defense. Since most of these services are offered through application programming interfaces (APIs) that still expose full or …

embry-riddle Repository record for In the Shadow of Prompts: Adversarial Attacks and Model Cloning in Large Language Models (opens in a new tab)