hydroxai Goto Github PK

anthropic-go

Go SDK for Anthropic's Claude, a next-generation AI assistant for your tasks, no matter the scale.

autodan

The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

bbq

Repository for the Bias Benchmark for QA dataset.

dra

[USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction"

drattack

Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

expo-updates-server

go-openai

OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go

gptfuzz

Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

jailbreakingllms

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

llm-past-tense

Does Refusal Training in LLMs Generalize to the Past Tense? [arXiv, July 2024]

react-native-logs

Performance-aware simple logger for React-Native and Expo with namespaces, custom levels and custom transports (colored console, file writing, etc.)

renellm

The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".

scribble-backend

Scribble api

scribble-frontend

Scribble RN app

tap

TAP: An automated jailbreaking method for black-box LLMs

textattack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

toxigen

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.