Projects sharing features with CipherChat

The respositiy is public package of the paper titled "Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues" submitted to ACL 2024.

📄 Paper • 🤗 Dataset

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models

FATE is an open-source federated learning platform that enables multiple organizations to collaboratively train machine learning models without exposing raw data to any party. It provides a complete framework for private data collaboration, allowing participants to jointly compute on sensitive information while maintaining data privacy and security guarantees through secure multi-party computation protocols. The platform distinguishes itself through its comprehensive infrastructure management capabilities, supporting automated deployment of multi-party clusters using Ansible-driven provisioni

FedML is a distributed machine learning training library, federated learning framework, and GPU workload orchestrator. It provides the core system components necessary to execute large-scale model training and fine-tuning across multi-cloud, on-premise, and decentralized GPU clusters, while offering a dedicated engine for scalable model serving and an MLOps pipeline manager for end-to-end lifecycle management. The platform distinguishes itself by enabling privacy-preserving federated learning across decentralized edge devices and organizational silos, keeping raw data on local hardware. It al

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).…

Google's differential privacy libraries.

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…

Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl

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.

Código fonte do App Mobile do PenhaS

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"

If this app helps you in any matter please consider donating

Training PyTorch models with differential privacy

Locus is a free, open source app for Android and iOS that allows you to share your location live. It encrypts your location end-to-end, meaning that no one, not even we, can read it. It stores the location decentralized on multiple servers of your choice using Nostr, meaning that you are not…

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".

NeMo-Guardrails is a toolkit for adding programmable safety constraints and dialogue boundaries to large language model conversational systems. It functions as security middleware that intercepts inputs and outputs to block prompt injections, jailbreaks, and sensitive data leaks, while providing a conversational dialogue manager to define structured interaction flows through configuration files. The framework includes a hallucination filter to screen model outputs for factual accuracy and a specialized modeling language for defining conversational flows and constraints. It provides capabiliti

This is the official repo of the paper "Attack Prompt Generation for Red Teaming and Defending Large Language Models" accepted to Findings of EMNLP 2023.