li-bangxin
Follow
Stars
[USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction"
MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.
[ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
JAILJUDGE: A comprehensive evaluation benchmark which includes a wide range of risk scenarios with complex malicious prompts (e.g., synthetic, adversarial, in-the-wild, and multi-language scenarios…
Universal and Transferable Attacks on Aligned Language Models
🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!
LLM steganography with minimum-entropy coupling - Hiding encrypted messages in natural language.
A program that provides LLMs with the ability to complete complex tasks using plugins.
This repository contains the code for the paper "Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks" by Abhinav Rao, Sachin Vashishta*, Atharva Naik*, Somak Aditya, a…
Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!
科研工作专用ChatGPT/GLM拓展，特别优化学术Paper润色体验，模块化设计支持自定义快捷按钮&函数插件，支持代码块表格显示，Tex公式双显示，新增Python和C++项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持gpt-3.5/gpt-4/chatglm
👮♂️The sensitive word tool for java.(敏感词/违禁词/违法词/脏词。基于 DFA 算法实现的高性能 java 敏感词过滤工具框架。内置支持单词标签分类分级。请勿发布涉及政治、广告、营销、翻墙、违反国家法律法规等内容。高性能敏感词检测过滤组件，附带繁体简体互换，支持全角半角互换，汉字转拼音，模糊搜索等功能。)
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
DSPy: The framework for programming—not prompting—language models
The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".
📖 《AI 辅助编程 Python 实战》这本书的大本营。
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复