yunwei37 / prompt-hacker-collections
prompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记
☆166Updated last month
Alternatives and similar repositories for prompt-hacker-collections:
Users that are interested in prompt-hacker-collections are comparing it to the libraries listed below
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆464Updated 6 months ago
- This repo includes ChatGPT jailbreaking prompts and some tests on its perference☆71Updated last year
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆178Updated 6 months ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆294Updated 5 months ago
- GPT-Analyst: A GPT for GPT analysis and reverse engineering☆197Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆153Updated 3 months ago
- 复旦白泽大模型安全基准测试集（2024年夏季版）☆35Updated 7 months ago
- Protect your GPTs through secure prompts to prevent malicious data leaks. 通过安全 Prompt 保护你的 GPTs ，避免内容被恶意泄露☆181Updated 3 months ago
- This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking cour…☆49Updated 2 months ago
- Agent Security Bench (ASB)☆66Updated last week
- LLM security and privacy☆48Updated 5 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆98Updated 2 months ago
- Multiple instructed-LLMs engage in multi-round "self-questioning" to seek the optimal solution, borrowing from the idea of debate, iterat…☆74Updated 7 months ago
- Hack OpenAI LLMs' System Prompts By Reverse Prompt Engineering☆63Updated last year
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆135Updated last year
- ☆121Updated 6 months ago
- CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.☆39Updated 4 months ago
- SC-Safety: 中文大模型多轮对抗安全基准☆128Updated last year
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆349Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆131Updated 3 months ago
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆180Updated 2 months ago
- Create your own GPT intelligent assistants using Azure OpenAI, Ollama, and local models, build and manage local knowledge bases, and expa…☆93Updated 7 months ago
- AutoAudit—— the LLM for Cyber Security 网络安全大语言模型☆317Updated last month
- ☆522Updated 3 months ago
- ☆55Updated last year
- Code for the website www.jailbreakchat.com☆85Updated last year
- ☆246Updated last year
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆202Updated 9 months ago
- Awesome LLM Jailbreak academic papers☆92Updated last year
- Papers and resources related to the security and privacy of LLMs 🤖☆489Updated 4 months ago