Stars
Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024
Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.
The lastest paper about detection of LLM-generated text and code
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)
Repository for Towards Codable Watermarking for Large Language Models
[NeurIPS2023] DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models
Implementation of 'A Watermark for Large Language Models' paper by Kirchenbauer & Geiping et. al.
The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".
Provable adversarial robustness at ImageNet scale
A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]
The AMLSim project is intended to provide a multi-agent based simulator that generates synthetic banking transaction data together with a set of known money laundering patterns - mainly for the pur…
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Natural Language Attacks in a Hard Label Black Box Setting.
An unofficial yet elegant interface of the ChatGPT API using browser automation that bypasses cloudflare detection and recaptchas.
A library to communicate with ChatGPT, Claude, Copilot, Gemini, HuggingChat, and Pi
Must-read Papers on Textual Adversarial Attack and Defense
An Open-Source Package for Textual Adversarial Attack.
A repository for the query-efficient black-box attack, SignHunter
腾讯柠檬清理是针对macOS系统专属制定的清理工具。主要功能包括重复文件和相似照片的识别、软件的定制化垃圾扫描、可视化的全盘空间分析、内存释放、浏览器隐私清理以及设备实时状态的监控等。重点聚焦清理功能，对上百款软件提供定制化的清理方案，提供专业的清理建议，帮助用户轻松完成一键式清理。
NeurIPS'22 | TransTab: Learning Transferable Tabular Transformers Across Tables
A repo for transfer learning with deep tabular models
Exploit for CVE-2021-22204 (ExifTool) - Arbitrary Code Execution