[NeurIPS'24 Spotlight] A comprehensive benchmark & codebase for Image manipulation detection/localization.
-
Updated
Sep 4, 2026 - Python
[NeurIPS'24 Spotlight] A comprehensive benchmark & codebase for Image manipulation detection/localization.
Official code for CAT-Net: Compression Artifact Tracing Network. Image manipulation detection and localization.
🏞 Steganography-based image integrity - Merkle tree nodes embedded into image chunks so that each chunk's integrity can be verified on its own.
[ECCV 2022] TAFIM: Targeted Adversarial Attacks against Facial Image Manipulation
The official repository of Real Text Manipulation (RTM)
Resolves severe noise in the widely spread CASIA2.0 dataset ground-truth for Image Manipulation Detection
Corrections of resolution issue for common image manipulation localization datasets. (CASIA, Coverage, IMD2020)
[ICME2021]The first work on Deep Inharmonious Region Localization, which can help image harmonization in an adversarial way.
[AAAI 2022] MadisNet: Inharmonious Region Localization by Magnifying Domain Discrepancy
Flask Web Interface to deploy ManTraNet and BusterNet for testing image manipulations
[CVPR 2026 Findings] Official repository for the paper "Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline".
Employ deep learning and transfer learning techniques to classify images as "fake" or "real," ensuring authenticity preservation.
DeepReveal is a deep learning-based image forensics system that performs pixel-level detection of AI-generated or manipulated image regions using U-Net segmentation, PyTorch, OpenCV, and Flask.
Fake Image Detection Using Machine Learning
Python software for detecting manipulation and multiple compression in images using advanced digital forensic techniques such as Benford's Law, noise analysis, and cloning detection.
NYU DS-UA 301 Final Project
Academic group project undertaken as part of a class.
Verifying ID information and check for manipulation in KYC systems.
Multi-agent AI image forensics pipeline that detects AI-generated and manipulated images using parallel vision agents (Gemini + Groq) with a context-aware pre-processing layer and Cerebras-based arbitration to reduce false positives.
To associate your repository with the image-manipulation-detection topic, visit your repo's landing page and select "manage topics."