判断内容是否可能由 AI 生成或修改。本页把适用场景、不能证明的事情、数据路径和证据标签放在工具数量之前。
AI 检测通常给出概率或分类信号，不能单独证明作弊、造假、侵权或作者身份。高影响场景应结合来源、过程记录、人工复核与申诉机制。
这些项目由分类规则自动发现。Stars、许可证、描述和活跃时间来自 GitHub；未完成本站核验，不等同于推荐。
This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext CNN is used to obtain a feature vector, further the LSTM layer is trained using the features. For more details follow the documentaion.
Research progress on speech deepfake detection: Relevant datasets aggregated from the review literature and publicly available codes
The offical repository of "SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model"
Benchmarking AI text detectors (GPTHumanizer, GPTZero, ZeroGPT, Sapling) across multiple datasets to evaluate accuracy, human false positive rates, and risk trade-offs.
[ACM CCS'24] SafeEar: Content Privacy-Preserving Audio Deepfake Detection
Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
A toolkit for benchmarking on a wide variety of audio deepfake datasets.
Code for paper "Audio Deepfake Detection with Self-supervised XLS-R and SLS classifier
🕵️♂️🔊 Automatically update Audio Deepfake Detection (ADD) papers daily using GitHub Actions (updates every 12 hours)