Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

[ICCV 2023] Official implementation of the paper: "DIRE for Diffusion-Generated Image Detection"

Official code for CAT-Net: Compression Artifact Tracing Network. Image manipulation detection and localization.

[CVPR 2022 Oral] Detecting Deepfakes with Self-Blended Images https://arxiv.org/abs/2204.08376

[CVPR'19, ICLR'20] A Python toolbox for modeling and optimization of photo acquisition & distribution pipelines (camera ISP, compression, forensics, manipulation detection)

[CVPR 2023 Highlight] Official implementation of the paper: "AltFreezing for More General Video Face Forgery Detection"

GAN-generated image detection based on CNNs

Detection of copy-move forgery in an image with CMDF methods. (SIFT, SURF, AKAZE, RANSAC)

Author implementation of Exploring Adversarial Fake Images on Face Manifold (CVPR 2021 oral)

VAAS is an inference-first, research-driven library for image integrity analysis. It integrates Vision Transformer Attention Mechanisms with patch-level self-consistency analysis to enable fine-grained localization and detection of visual inconsistencies across diverse image analysis tasks.

Computer Graphics vs Real Photographic Images : A Deep-learning approach

Extract camera fingerprint using different types of state-of-the-art denoisers

Implementation of the paper A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer

Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

Code for paper "Distinguishing Computer-Generated Images from Natural Images Using Channel and Pixel Correlation"

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

Zero-shot AI-generated image detection using forensic self-descriptions. Trained only on real images, detects deepfakes from any generator. Official implementation. CVPR 2025.

A Python-based desktop tool for detecting digital image forgeries. It applies forensic techniques—Error Level Analysis, Metadata Extraction, Histogram, Noise Map, JPEG Ghost, and Copy-Move Detection—to reveal inconsistencies and visual clues, helping experts assess image authenticity without automation.

Detecting Image Attribution for Text-to-Image Diffusion Models in RGB and Beyond

Offline image forensics and deepfake detection from your terminal. Analyzes pixel-level artifacts, metadata, and facial consistency. No API required.