RAID is the largest and most challenging benchmark for AI-generated text detection. (ACL 2024)
An awesome list of the best AI content detectors.
[AAAI 2024] The official repository for our paper, "OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples"
A lightweight Chromium extension that transparently strips out hidden watermark markers from ChatGPT outputs before they ever reach your clipboard.
A curated list of awesome AI countermeasures - tools, models, datasets and research for detecting AI-generated content, from LLM-written text to deepfake images, video and audio.
Live crowdsourced research platform measuring how well humans detect AI-generated news - dual-axis authenticity judgments, gamified challenge mode & shareable score cards. The human-perception half of the RogueGPT pipeline.
MGTEval, an interactive platform for systematic evaluation of ai-generated text detectors, supporting 25+ detectors including DetectGPT, Fast-DetectGPT, Binoculars, and more.
[EMNLP 2024] The official repository for our paper, "How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection"
Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.
ChatGPT-generated texts for automated ChatGPT detection
HSE bachelor's thesis on detecting machine-generated text via semantic trajectories, graph features and classification.
Local-first toolkit for detecting AI-generated text and disrupting classical detectors plus statistical LLM watermarks (SynthID-Text / tournament-sampling style).
Два скилла для работы с русским текстом: проверка на следы ИИ и письмо с нуля
🔍 基于BERT的MBA论文AIGC风险检测系统 | BERT-based MBA Thesis AIGC Detection System with 96.7% F1 Score. Complete S1-S8 pipeline for academic integrity.
Remove AI watermarks, invisible Unicode, and C2PA/EXIF/XMP provenance metadata from text and files (PDF, DOCX, ODT, PNG, JPEG, SVG, HTML, Markdown). Python, no dependencies for text cleaning." This is slightly updated from before to reflect the new DOCX/ODT/PDF support
Toxicity evaluation on DeepSeek R1 and DeepSeek API
Analysis of 13 years of BBC articles (2012–2025) using the isFake.ai AI text detector.
Linter for Persian (Farsi) content: catches AI-generated tells, missing ZWNJ (نیمفاصله), Arabic letters, mojibake and SEO length budgets. Zero dependencies, CI-ready.
Визуальная новелла с элементами RPG в сеттинге киберпанка с генерацией контента с помощью ИИ
Deep learning project for classifying text sources as Human, Google, Meta, Anthropic or OpenAI.
To associate your repository with the ai-generated-text topic, visit your repo's landing page and select "manage topics."