Stars
Code for replicating experiments in our paper (accepted by AAAI-24).
PyTorch implementation of adversarial attacks [torchattacks]
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)
Implementation of CVPR 2022 paper "Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations"
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models
The official GitHub page for the survey paper "A Survey on Mixture of Experts in Large Language Models".
Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).
Code for our S&P'21 paper: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
[USENIX Security'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models
Universal Adversarial Perturbations (UAPs) for PyTorch
[ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning
This repository is an implementation of the paper ModelGiF: Gradient Fields for Model Functional Distance (ICCV2023)
Code for paper: "RemovalNet: DNN model fingerprinting removal attack", IEEE TDSC 2023.
python library for invisible image watermark (blind image watermark)
For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
A collection of prompts, system prompts and LLM instructions
Machine Learning and Computer Vision Engineer - Technical Interview Questions
Evaluating Durability: Benchmark Insights into Multimodal Watermarking
AudioLDM: Generate speech, sound effects, music and beyond, with text.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model