π Paper π¦ GitHub π€ Hugging Face | Modelscope
The main features of zihao-ai/bot are: Jailbreak Attack Methods.
Open-source alternatives to zihao-ai/bot include: agencyenterprise/promptinject β PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of theβ¦ cam-fss/jailbreak-langchain β In this paper, we conduct the first work to propose the concept of indirect jailbreak and achieve Retrieval-Augmentedβ¦ chawins/pal β Chawin Sitawarin 1 Norman Mu 1 David Wagner 1 Alexandre Araujo 2. czycurefun/ijbr β The respositiy is public package of the paper titled "Play Guessing Game with LLM: Indirect Jailbreak Attack withβ¦ damo-nlp-sg/multilingual-safety-for-llms β π Paper β’ π€ Dataset. aatrox103/sap β This is the official repo of the paper "Attack Prompt Generation for Red Teaming and Defending Large Language Models"β¦
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. π Best Paper Awards @ NeurIPS ML Safety Workshop 2022
In this paper, we conduct the first work to propose the concept of indirect jailbreak and achieve Retrieval-Augmented Generation (RAG) via LangChain. Building on this, we further design a novel method of indirect jailbreak attack, termed Poisoned-LangChain (PLC), which leverages a poisonedβ¦
This is the official repo of the paper "Attack Prompt Generation for Red Teaming and Defending Large Language Models" accepted to Findings of EMNLP 2023.
