Open-source alternatives to DarkCite

📄 Paper • 🤗 Dataset

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models

This repository is for our new work: "BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit", feel free to propose your issues!! 😎

This is the source code for the ICLR 2024 paper "An LLM can Fool Itself: A Prompt-Based Adversarial Attack", Xilie Xu (NUS), Keyi Kong (SDU), Ning Liu (SDU), Lizhen Cui (SDU), Di Wang (KAUST), Jingfeng Zhang (University of Auckland/RIKEN-AIP), Mohan Kankanhalli (NUS).…

We present a new class of vulnerabilities and impacts stemming from "indirect prompt injection" affecting language models integrated with applications. Our demos currently span GPT-4 (Bing and synthetic apps) using ChatML, GPT-3 & LangChain based apps in addition to proof-of-concepts for attacks…

Paper Link: https://arxiv.org/pdf/2304.05197.pdf

This repository contains the code implementation for the paper CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

Logo generated by GPT-4

This is the replication package for the paper MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots.

Code for our NAACL 2024 Paper "Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking"

Official implementation for "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"

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

This repository contains a PyTorch implementation for our paper Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation.

QROA, or Query-Response Optimization Attack, is an innovative and robust strategy designed to explore and exploit vulnerabilities in Large Language Models (LLMs) through black-box interactions. This method leverages optimized triggers embedded within benign-looking instructions to manipulate…

This repository contains code and data for "FUZZLLM: A Novel and Universal Fuzzing Framework for Discovering Jailbreak Vulnerabilities in LLMs" (accepted to ICASSP 2024). Our work was also invited to be presented at one of the top hacker conventions – ShmooCon 2024. arXiv

Abstract. While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (TAP), an automated method for…

A framework to evaluate the generalization capability of safety alignment for LLMs

The official implementation of our technical report "AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling" by Xiaogeng Liu and Chaowei Xiao.

AutoDAN-Turbo Official Website at HERE

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

ToxASCII is the official code repository accompanying the paper "Read Over the Lines: Attacking LLMs and Toxicity Detection Systems with ASCII Art to Mask Profanity," available on arXiv. This repository provides the necessary tools and data to replicate the experiments detailed in the paper,…

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

This repository has moved and is no longer maintained! Please visit qcri/StructTransformBench for the latest updates.