Abstract: In this paper, we propose a novel classification method that utilizes syntax trees and perplexity to identify jailbreak attacks that use hostile suffixes to make large language models (LLMs) ...

🔍 Use only the plugins you need for better performance and bundle size. 🧠 You can use official plugins, or build your own custom ones to keep the bundle size ...

Abstract: In this paper, we present a curated collection of 2833 C# solutions taken from Github. We encode the data in a new intermediate representation (IR) that facilitates further analysis by ...