Best AI tools for< Jailbreak Llms >

Adversa AI is a platform that provides Secure AI Awareness, Assessment, and Assurance solutions for various industries to mitigate AI risks. The platform focuses on LLM Security, Privacy, Jailbreaks, Red Teaming, Chatbot Security, and AI Face Recognition Security. Adversa AI helps enable AI transformation by protecting it from cyber threats, privacy issues, and safety incidents. The platform offers comprehensive research, advisory services, and expertise in the field of AI security.

This is the official repository for the ACM CCS 2024 paper 'Do Anything Now': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. The project employs a new framework called JailbreakHub to conduct the first measurement study on jailbreak prompts in the wild, collecting 15,140 prompts from December 2022 to December 2023, including 1,405 jailbreak prompts. The dataset serves as the largest collection of in-the-wild jailbreak prompts. The repository contains examples of harmful language and is intended for research purposes only.

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, and exciting jailbreak methods on Large Language Models (LLMs). The repository contains papers, codes, datasets, evaluations, and analyses related to jailbreak attacks on LLMs. It serves as a comprehensive resource for researchers and practitioners interested in exploring various jailbreak techniques and defenses in the context of LLMs. Contributions such as additional jailbreak-related content, pull requests, and issue reports are welcome, and contributors are acknowledged. For any inquiries or issues, contact [email protected]. If you find this repository useful for your research or work, consider starring it to show appreciation.

This repository contains code and results for jailbreaking leading safety-aligned LLMs with simple adaptive attacks. We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. We demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token ``Sure''), potentially with multiple restarts. In this way, we achieve nearly 100% attack success rate---according to GPT-4 as a judge---on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models---that do not expose logprobs---via either a transfer or prefilling attack with 100% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models---a task that shares many similarities with jailbreaking---which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection).

This repository serves as a practical guide for Medical Large Language Models (Medical LLMs) and provides resources, surveys, and tools for building, fine-tuning, and utilizing LLMs in the medical domain. It covers a wide range of topics including pre-training, fine-tuning, downstream biomedical tasks, clinical applications, challenges, future directions, and more. The repository aims to provide insights into the opportunities and challenges of LLMs in medicine and serve as a practical resource for constructing effective medical LLMs.

Arch is an intelligent Layer 7 gateway designed to protect, observe, and personalize LLM applications with APIs. It handles tasks like detecting and rejecting jailbreak attempts, calling backend APIs, disaster recovery, and observability. Built on Envoy Proxy, it offers features like function calling, prompt guardrails, traffic management, and standards-based observability. Arch aims to improve the speed, security, and personalization of generative AI applications.

Awesome_GPT_Super_Prompting is a repository that provides resources related to Jailbreaks, Leaks, Injections, Libraries, Attack, Defense, and Prompt Engineering. It includes information on ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, and Adversarial Machine Learning. The repository contains curated lists of repositories, tools, and resources related to GPTs, prompt engineering, prompt libraries, and secure prompting. It also offers insights into Cyber-Albsecop GPT Agents and Super Prompts for custom GPT usage.

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.

Awesome LLM Security is a curated collection of tools, documents, and projects related to Large Language Model (LLM) security. It covers various aspects of LLM security including white-box, black-box, and backdoor attacks, defense mechanisms, platform security, and surveys. The repository provides resources for researchers and practitioners interested in understanding and safeguarding LLMs against adversarial attacks. It also includes a list of tools specifically designed for testing and enhancing LLM security.

OpenRedTeaming is a repository focused on red teaming for generative models, specifically large language models (LLMs). The repository provides a comprehensive survey on potential attacks on GenAI and robust safeguards. It covers attack strategies, evaluation metrics, benchmarks, and defensive approaches. The repository also implements over 30 auto red teaming methods. It includes surveys, taxonomies, attack strategies, and risks related to LLMs. The goal is to understand vulnerabilities and develop defenses against adversarial attacks on large language models.

The 'Dive into Large Language Models' series programming practice tutorial is an extension of the 'Artificial Intelligence Security Technology' course lecture notes from Shanghai Jiao Tong University (Instructor: Zhang Zhuosheng). It aims to provide introductory programming references related to large models. Through simple practice, it helps students quickly grasp large models, better engage in course design, or academic research. The tutorial covers topics such as fine-tuning and deployment, prompt learning and thought chains, knowledge editing, model watermarking, jailbreak attacks, multimodal models, large model intelligent agents, and security. Disclaimer: The content is based on contributors' personal experiences, internet data, and accumulated research work, provided for reference only.

COLD-Attack is a framework designed for controllable jailbreaks on large language models (LLMs). It formulates the controllable attack generation problem and utilizes the Energy-based Constrained Decoding with Langevin Dynamics (COLD) algorithm to automate the search of adversarial LLM attacks with control over fluency, stealthiness, sentiment, and left-right-coherence. The framework includes steps for energy function formulation, Langevin dynamics sampling, and decoding process to generate discrete text attacks. It offers diverse jailbreak scenarios such as fluent suffix attacks, paraphrase attacks, and attacks with left-right-coherence.

TrustLLM is a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. The document explains how to use the trustllm python package to help you assess the performance of your LLM in trustworthiness more quickly. For more details about TrustLLM, please refer to project website.

Agentic Security is an open-source vulnerability scanner designed for safety scanning, offering customizable rule sets and agent-based attacks. It provides comprehensive fuzzing for any LLMs, LLM API integration, and stress testing with a wide range of fuzzing and attack techniques. The tool is not a foolproof solution but aims to enhance security measures against potential threats. It offers installation via pip and supports quick start commands for easy setup. Users can utilize the tool for LLM integration, adding custom datasets, running CI checks, extending dataset collections, and dynamic datasets with mutations. The tool also includes a probe endpoint for integration testing. The roadmap includes expanding dataset variety, introducing new attack vectors, developing an attacker LLM, and integrating OWASP Top 10 classification.

A comprehensive repository focusing on 'Model Merging in LLMs, MLLMs, and Beyond', providing an exhaustive overview of model merging methods, theories, applications, and future research directions. The repository covers various advanced methods, applications in foundation models, different machine learning subfields, and tasks like pre-merging methods, architecture transformation, weight alignment, basic merging methods, and more.

last_layer is a security library designed to protect LLM applications from prompt injection attacks, jailbreaks, and exploits. It acts as a robust filtering layer to scrutinize prompts before they are processed by LLMs, ensuring that only safe and appropriate content is allowed through. The tool offers ultra-fast scanning with low latency, privacy-focused operation without tracking or network calls, compatibility with serverless platforms, advanced threat detection mechanisms, and regular updates to adapt to evolving security challenges. It significantly reduces the risk of prompt-based attacks and exploits but cannot guarantee complete protection against all possible threats.

This repository tracks the latest research on machine unlearning in large language models (LLMs). It offers a comprehensive list of papers, datasets, and resources relevant to the topic.

The 'llm-misinformation-survey' repository is dedicated to the survey on combating misinformation in the age of Large Language Models (LLMs). It explores the opportunities and challenges of utilizing LLMs to combat misinformation, providing insights into the history of combating misinformation, current efforts, and future outlook. The repository serves as a resource hub for the initiative 'LLMs Meet Misinformation' and welcomes contributions of relevant research papers and resources. The goal is to facilitate interdisciplinary efforts in combating LLM-generated misinformation and promoting the responsible use of LLMs in fighting misinformation.

This game combines humor and challenge, offering players a laugh-filled journey through the world of cybersecurity and AI.

Volle Freiheit