A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.

Frida script to bypass the iOS application Jailbreak Detection

Does Refusal Training in LLMs Generalize to the Past Tense? [NeurIPS 2024 Safe Generative AI Workshop (Oral)]

Python adaptation for pelara1n

An extensive prompt to make a friendly persona from a chatbot-like model like ChatGPT

Cydia repo

Security Kit is a lightweight framework that helps to achieve a security layer

During the Development of Suave7 and it's Predecessors, we've created a lot of Icons and UI-Images and we would like to share them with you. The Theme Developer Kit contains nearly 5.600 Icons, more than 380 Photoshop-Templates and 100 Pixelmator-Documents. With this Package you can customize every App from the App Store …

iOS APT distribution repository for rootful and rootless jailbreaks

Customizable Dark Mode Extension for iOS 13+

Materials for the course Principles of AI: LLMs at UPenn (Stat 9911, Spring 2025). LLM architectures, training paradigms (pre- and post-training, alignment), test-time computation, reasoning, safety and robustness (jailbreaking, oversight, uncertainty), representations, interpretability (circuits), etc.

Source code for bypass tweaks hosted under https://github.com/hekatos/repo. Licensed under 0BSD except submodules

LV-Crew.org_(LVC)_-_Howto_-_iPhones

This repository contains the code for the paper "Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks" by Abhinav Rao, Sachin Vashishta*, Atharva Naik*, Somak Aditya, and Monojit Choudhury, accepted at LREC-CoLING 2024

Your best llm security paper library

Updater script for iOS-OTA-Downgrader.

boot-script

📖 Full iOS 11 jailbreaking guide

HITC reborn: faster, better and prettier

"ChatGPT Evil Confidant Mode" delves into a controversial and unethical use of AI, highlighting how specific prompts can generate harmful and malicious responses from ChatGPT.