
CJA_Comprehensive_Jailbreak_Assessment
This is the public code repository of paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'
Stars: 122

This public repository contains the paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'. It provides a labeling method to label results using Python and offers the opportunity to submit evaluation results to the leaderboard. Full codes will be released after the paper is accepted.
README:
This is the public repository of the paper Comprehensive Assessment of Jailbreak Attacks Against LLMs.
The following updates will be released first on the official repository in the future.
Be careful! This repository may contain harmful/offensive responses. Users need to use this repository responsibly.
- Clone this repository.
- Prepare the python ENV.
conda create -n CJA python=3.10
conda activate CJA
cd PATH_TO_THE_REPOSITORY
pip install -r requirements.txt
Option 1: label single file
- Switch directory:
cd ./scripts_label
- Command to label single file:
python label.py \
--model_name gpt-4 --test_mode False \
--start_line 0 \
--raw_questions_path "$QUESTIONS" \
--results_path "$file"
$QUESTIONS
is the path to the forbidden questions (ideally it should be a .csv
file, refer to ./forbidden_questions/forbidden_questions.csv for example).
$file
is the path to the LLM responses after jailbreak, it should be a .json
file. The .json
file could be generated by the following codes.
answers.append({'response': answer})
# Write into the output file
with open(output_file, 'w') as out_file:
json.dump(answers, out_file, indent=4)
Note that answer
is the response from the target LLM suffering jailbreak attacks.
Option 2: label files in a directory
You may also utilize label.sh to label files in a directory:
bash label.sh PATH_TO_RESPONSES_DIRECTORY
The files storing the labels will be saved to the same directory where you store the jailbreak responses.
NOTE: We have omitted the harmful responses related to the project. For example, the few-shot examples in scripts_label/label.py. Feel free to use your own examples.
- Switch directory:
cd ./scripts_defense
- Execute the defense:
bash ./defense_execute.sh DEFENSE_METHOD PATH_TO_YOUR_ADV_PROMPTS_FOLDER
Currently, seven defense methods are supported (refer to ./scripts_defense/defense_execute.sh for details).
The adv prompts folder should follow such a structure:
example_adv_prompts
└─ adv_basic.json
The .json
file could be obtained by the following codes:
adv_prompts = [prompt_1, prompt_2, ...] # a list of adv prompts
json_file = OUTPUT_PATH
with open(json_file, 'w') as outfile:
json.dump(adv_prompts, outfile, indent=4)
Refer to folder ./example_adv_prompts for an example.
Welcome to submit your own evaluation results (steps = 50) of jailbreak attacks to us. The leaderboard is available here.
Full codes will be released after the paper is accepted.
- [ ] Check the env file requirements.txt.
- [ ] Test the guide in the README.md.
- [ ] Clean the codes/comments.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for CJA_Comprehensive_Jailbreak_Assessment
Similar Open Source Tools

CJA_Comprehensive_Jailbreak_Assessment
This public repository contains the paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'. It provides a labeling method to label results using Python and offers the opportunity to submit evaluation results to the leaderboard. Full codes will be released after the paper is accepted.

vulnerability-analysis
The NVIDIA AI Blueprint for Vulnerability Analysis for Container Security showcases accelerated analysis on common vulnerabilities and exposures (CVE) at an enterprise scale, reducing mitigation time from days to seconds. It enables security analysts to determine software package vulnerabilities using large language models (LLMs) and retrieval-augmented generation (RAG). The blueprint is designed for security analysts, IT engineers, and AI practitioners in cybersecurity. It requires NVAIE developer license and API keys for vulnerability databases, search engines, and LLM model services. Hardware requirements include L40 GPU for pipeline operation and optional LLM NIM and Embedding NIM. The workflow involves LLM pipeline for CVE impact analysis, utilizing LLM planner, agent, and summarization nodes. The blueprint uses NVIDIA NIM microservices and Morpheus Cybersecurity AI SDK for vulnerability analysis.

aiid
The Artificial Intelligence Incident Database (AIID) is a collection of incidents involving the development and use of artificial intelligence (AI). The database is designed to help researchers, policymakers, and the public understand the potential risks and benefits of AI, and to inform the development of policies and practices to mitigate the risks and promote the benefits of AI. The AIID is a collaborative project involving researchers from the University of California, Berkeley, the University of Washington, and the University of Toronto.

OnAIR
The On-board Artificial Intelligence Research (OnAIR) Platform is a framework that enables AI algorithms written in Python to interact with NASA's cFS. It is intended to explore research concepts in autonomous operations in a simulated environment. The platform provides tools for generating environments, handling telemetry data through Redis, running unit tests, and contributing to the repository. Users can set up a conda environment, configure telemetry and Redis examples, run simulations, and conduct unit tests to ensure the functionality of their AI algorithms. The platform also includes guidelines for licensing, copyright, and contributions to the repository.

vectara-answer
Vectara Answer is a sample app for Vectara-powered Summarized Semantic Search (or question-answering) with advanced configuration options. For examples of what you can build with Vectara Answer, check out Ask News, LegalAid, or any of the other demo applications.

magic-cli
Magic CLI is a command line utility that leverages Large Language Models (LLMs) to enhance command line efficiency. It is inspired by projects like Amazon Q and GitHub Copilot for CLI. The tool allows users to suggest commands, search across command history, and generate commands for specific tasks using local or remote LLM providers. Magic CLI also provides configuration options for LLM selection and response generation. The project is still in early development, so users should expect breaking changes and bugs.

tonic_validate
Tonic Validate is a framework for the evaluation of LLM outputs, such as Retrieval Augmented Generation (RAG) pipelines. Validate makes it easy to evaluate, track, and monitor your LLM and RAG applications. Validate allows you to evaluate your LLM outputs through the use of our provided metrics which measure everything from answer correctness to LLM hallucination. Additionally, Validate has an optional UI to visualize your evaluation results for easy tracking and monitoring.

cortex
Cortex is a tool that simplifies and accelerates the process of creating applications utilizing modern AI models like chatGPT and GPT-4. It provides a structured interface (GraphQL or REST) to a prompt execution environment, enabling complex augmented prompting and abstracting away model connection complexities like input chunking, rate limiting, output formatting, caching, and error handling. Cortex offers a solution to challenges faced when using AI models, providing a simple package for interacting with NL AI models.

probsem
ProbSem is a repository that provides a framework to leverage large language models (LLMs) for assigning context-conditional probability distributions over queried strings. It supports OpenAI engines and HuggingFace CausalLM models, and is flexible for research applications in linguistics, cognitive science, program synthesis, and NLP. Users can define prompts, contexts, and queries to derive probability distributions over possible completions, enabling tasks like cloze completion, multiple-choice QA, semantic parsing, and code completion. The repository offers CLI and API interfaces for evaluation, with options to customize models, normalize scores, and adjust temperature for probability distributions.

askrepo
askrepo is a tool that reads the content of Git-managed text files in a specified directory, sends it to the Google Gemini API, and provides answers to questions based on a specified prompt. It acts as a question-answering tool for source code by using a Google AI model to analyze and provide answers based on the provided source code files. The tool leverages modules for file processing, interaction with the Google AI API, and orchestrating the entire process of extracting information from source code files.

slack-bot
The Slack Bot is a tool designed to enhance the workflow of development teams by integrating with Jenkins, GitHub, GitLab, and Jira. It allows for custom commands, macros, crons, and project-specific commands to be implemented easily. Users can interact with the bot through Slack messages, execute commands, and monitor job progress. The bot supports features like starting and monitoring Jenkins jobs, tracking pull requests, querying Jira information, creating buttons for interactions, generating images with DALL-E, playing quiz games, checking weather, defining custom commands, and more. Configuration is managed via YAML files, allowing users to set up credentials for external services, define custom commands, schedule cron jobs, and configure VCS systems like Bitbucket for automated branch lookup in Jenkins triggers.

WindowsAgentArena
Windows Agent Arena (WAA) is a scalable Windows AI agent platform designed for testing and benchmarking multi-modal, desktop AI agents. It provides researchers and developers with a reproducible and realistic Windows OS environment for AI research, enabling testing of agentic AI workflows across various tasks. WAA supports deploying agents at scale using Azure ML cloud infrastructure, allowing parallel running of multiple agents and delivering quick benchmark results for hundreds of tasks in minutes.

LongRAG
This repository contains the code for LongRAG, a framework that enhances retrieval-augmented generation with long-context LLMs. LongRAG introduces a 'long retriever' and a 'long reader' to improve performance by using a 4K-token retrieval unit, offering insights into combining RAG with long-context LLMs. The repo provides instructions for installation, quick start, corpus preparation, long retriever, and long reader.

OlympicArena
OlympicArena is a comprehensive benchmark designed to evaluate advanced AI capabilities across various disciplines. It aims to push AI towards superintelligence by tackling complex challenges in science and beyond. The repository provides detailed data for different disciplines, allows users to run inference and evaluation locally, and offers a submission platform for testing models on the test set. Additionally, it includes an annotation interface and encourages users to cite their paper if they find the code or dataset helpful.

aiexe
aiexe is a cutting-edge command-line interface (CLI) and graphical user interface (GUI) tool that integrates powerful AI capabilities directly into your terminal or desktop. It is designed for developers, tech enthusiasts, and anyone interested in AI-powered automation. aiexe provides an easy-to-use yet robust platform for executing complex tasks with just a few commands. Users can harness the power of various AI models from OpenAI, Anthropic, Ollama, Gemini, and GROQ to boost productivity and enhance decision-making processes.

OpenAI-sublime-text
The OpenAI Completion plugin for Sublime Text provides first-class code assistant support within the editor. It utilizes LLM models to manipulate code, engage in chat mode, and perform various tasks. The plugin supports OpenAI, llama.cpp, and ollama models, allowing users to customize their AI assistant experience. It offers separated chat histories and assistant settings for different projects, enabling context-specific interactions. Additionally, the plugin supports Markdown syntax with code language syntax highlighting, server-side streaming for faster response times, and proxy support for secure connections. Users can configure the plugin's settings to set their OpenAI API key, adjust assistant modes, and manage chat history. Overall, the OpenAI Completion plugin enhances the Sublime Text editor with powerful AI capabilities, streamlining coding workflows and fostering collaboration with AI assistants.
For similar tasks

CJA_Comprehensive_Jailbreak_Assessment
This public repository contains the paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'. It provides a labeling method to label results using Python and offers the opportunity to submit evaluation results to the leaderboard. Full codes will be released after the paper is accepted.

farfalle
Farfalle is an open-source AI-powered search engine that allows users to run their own local LLM or utilize the cloud. It provides a tech stack including Next.js for frontend, FastAPI for backend, Tavily for search API, Logfire for logging, and Redis for rate limiting. Users can get started by setting up prerequisites like Docker and Ollama, and obtaining API keys for Tavily, OpenAI, and Groq. The tool supports models like llama3, mistral, and gemma. Users can clone the repository, set environment variables, run containers using Docker Compose, and deploy the backend and frontend using services like Render and Vercel.

chatllm.cpp
ChatLLM.cpp is a pure C++ implementation tool for real-time chatting with RAG on your computer. It supports inference of various models ranging from less than 1B to more than 300B. The tool provides accelerated memory-efficient CPU inference with quantization, optimized KV cache, and parallel computing. It allows streaming generation with a typewriter effect and continuous chatting with virtually unlimited content length. ChatLLM.cpp also offers features like Retrieval Augmented Generation (RAG), LoRA, Python/JavaScript/C bindings, web demo, and more possibilities. Users can clone the repository, quantize models, build the project using make or CMake, and run quantized models for interactive chatting.

airdcpp-windows
AirDC++ for Windows 10/11 is a file sharing client with a focus on ease of use and performance. It is designed to provide a seamless experience for users looking to share and download files over the internet. The tool is built using Visual Studio 2022 and offers a range of features to enhance the file sharing process. Users can easily clone the repository to access the latest version and contribute to the development of the tool.

oaic
Open AI Cellular is the core software for Open AI Cellular. It provides documentation on installation, quick start guide, and usage. The repository contains submodules and requires sphinx with the read-the-docs theme for building core documentation. The resulting documentation is stored in the 'docs/build/html' directory.

FireRedTTS
FireRedTTS is a foundation text-to-speech framework designed for industry-level generative speech applications. It offers a rich-punctuation model with expanded punctuation coverage and enhanced audio production consistency. The tool provides pre-trained checkpoints, inference code, and an interactive demo space. Users can clone the repository, create a conda environment, download required model files, and utilize the tool for synthesizing speech in various languages. FireRedTTS aims to enhance stability and provide controllable human-like speech generation capabilities.
For similar jobs

ciso-assistant-community
CISO Assistant is a tool that helps organizations manage their cybersecurity posture and compliance. It provides a centralized platform for managing security controls, threats, and risks. CISO Assistant also includes a library of pre-built frameworks and tools to help organizations quickly and easily implement best practices.

PurpleLlama
Purple Llama is an umbrella project that aims to provide tools and evaluations to support responsible development and usage of generative AI models. It encompasses components for cybersecurity and input/output safeguards, with plans to expand in the future. The project emphasizes a collaborative approach, borrowing the concept of purple teaming from cybersecurity, to address potential risks and challenges posed by generative AI. Components within Purple Llama are licensed permissively to foster community collaboration and standardize the development of trust and safety tools for generative AI.

vpnfast.github.io
VPNFast is a lightweight and fast VPN service provider that offers secure and private internet access. With VPNFast, users can protect their online privacy, bypass geo-restrictions, and secure their internet connection from hackers and snoopers. The service provides high-speed servers in multiple locations worldwide, ensuring a reliable and seamless VPN experience for users. VPNFast is easy to use, with a user-friendly interface and simple setup process. Whether you're browsing the web, streaming content, or accessing sensitive information, VPNFast helps you stay safe and anonymous online.

taranis-ai
Taranis AI is an advanced Open-Source Intelligence (OSINT) tool that leverages Artificial Intelligence to revolutionize information gathering and situational analysis. It navigates through diverse data sources like websites to collect unstructured news articles, utilizing Natural Language Processing and Artificial Intelligence to enhance content quality. Analysts then refine these AI-augmented articles into structured reports that serve as the foundation for deliverables such as PDF files, which are ultimately published.

NightshadeAntidote
Nightshade Antidote is an image forensics tool used to analyze digital images for signs of manipulation or forgery. It implements several common techniques used in image forensics including metadata analysis, copy-move forgery detection, frequency domain analysis, and JPEG compression artifacts analysis. The tool takes an input image, performs analysis using the above techniques, and outputs a report summarizing the findings.

h4cker
This repository is a comprehensive collection of cybersecurity-related references, scripts, tools, code, and other resources. It is carefully curated and maintained by Omar Santos. The repository serves as a supplemental material provider to several books, video courses, and live training created by Omar Santos. It encompasses over 10,000 references that are instrumental for both offensive and defensive security professionals in honing their skills.

AIMr
AIMr is an AI aimbot tool written in Python that leverages modern technologies to achieve an undetected system with a pleasing appearance. It works on any game that uses human-shaped models. To optimize its performance, users should build OpenCV with CUDA. For Valorant, additional perks in the Discord and an Arduino Leonardo R3 are required.

admyral
Admyral is an open-source Cybersecurity Automation & Investigation Assistant that provides a unified console for investigations and incident handling, workflow automation creation, automatic alert investigation, and next step suggestions for analysts. It aims to tackle alert fatigue and automate security workflows effectively by offering features like workflow actions, AI actions, case management, alert handling, and more. Admyral combines security automation and case management to streamline incident response processes and improve overall security posture. The tool is open-source, transparent, and community-driven, allowing users to self-host, contribute, and collaborate on integrations and features.