# Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization

arXiv: https://arxiv.org/abs/2107.02434 · HTML: https://mlsanity.com/paper/2107.02434/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [Learning Rich Features for Image Manipulation Detection](https://mlsanity.com/paper/1805.04953/) (2018)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization](https://mlsanity.com/paper/2009.00726/) (2020)
- [Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)](https://mlsanity.com/paper/1709.02016/) (2017)
- [Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries](https://mlsanity.com/paper/1903.02495/) (2019)
- [WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images](https://mlsanity.com/paper/1803.04805/) (2018)

## Built on by (most cited first, 24 of 24)

- [Pixel-Inconsistency Modeling for Image Manipulation Localization](https://mlsanity.com/paper/2310.00234/) (2023)
- [Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning](https://mlsanity.com/paper/2309.14900/) (2023)
- [The Age of Synthetic Realities: Challenges and Opportunities](https://mlsanity.com/paper/2306.11503/) (2023)
- [Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusion](https://mlsanity.com/paper/2309.09306/) (2023)
- [Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization](https://mlsanity.com/paper/2406.13565/) (2024)
- [ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization](https://mlsanity.com/paper/2410.10238/) (2024)
- [TBFormer: Two-Branch Transformer for Image Forgery Localization](https://mlsanity.com/paper/2302.13004/) (2023)
- [Fusion Transformer with Object Mask Guidance for Image Forgery Analysis](https://mlsanity.com/paper/2403.12229/) (2024)
- [Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization](https://mlsanity.com/paper/2408.02306/) (2024)
- [Effective Image Tampering Localization with Multi-Scale ConvNeXt Feature Fusion](https://mlsanity.com/paper/2208.13739/) (2022)
- [Progressive Feedback-Enhanced Transformer for Image Forgery Localization](https://mlsanity.com/paper/2311.08910/) (2023)
- [Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization](https://mlsanity.com/paper/2504.05224/) (2025)
- [Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption](https://mlsanity.com/paper/2207.10402/) (2022)
- [Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images](https://mlsanity.com/paper/2209.10700/) (2022)
- [Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation](https://mlsanity.com/paper/2508.20987/) (2025)
- [Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos](https://mlsanity.com/paper/2112.08117/) (2021)
- [Image Harmonization with Region-wise Contrastive Learning](https://mlsanity.com/paper/2205.14058/) (2022)
- [MSMG-Net: Multi-scale Multi-grained Supervised Metworks for Multi-task Image Manipulation Detection and Localization](https://mlsanity.com/paper/2211.03140/) (2022)
- [Evading Detection Actively: Toward Anti-Forensics against Forgery Localization](https://mlsanity.com/paper/2310.10036/) (2023)
- [CLUE: Leveraging Low-Rank Adaptation to Capture Latent Uncovered Evidence for Image Forgery Localization](https://mlsanity.com/paper/2508.07413/) (2025)
- [TriPINet: Tripartite Progressive Integration Network for Image Manipulation Localization](https://mlsanity.com/paper/2212.12841/) (2022)
- [Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective](https://mlsanity.com/paper/2408.03944/) (2024)
- [SDiFL: Stable Diffusion-Driven Framework for Image Forgery Localization](https://mlsanity.com/paper/2508.20182/) (2025)
- [CBDiff:Conditional Bernoulli Diffusion Models for Image Forgery Localization](https://mlsanity.com/paper/2510.19597/) (2025)

## Abstract (arXiv)

Image editing techniques enable people to modify the content of an image without leaving visual traces and thus may cause serious security risks. Hence the detection and localization of these forgeries become quite necessary and challenging. Furthermore, unlike other tasks with extensive data, there is usually a lack of annotated forged images for training due to annotation difficulties. In this paper, we propose a self-adversarial training strategy and a reliable coarse-to-fine network that utilizes a self-attention mechanism to localize forged regions in forgery images. The self-attention module is based on a Channel-Wise High Pass Filter block (CW-HPF). CW-HPF leverages inter-channel relationships of features and extracts noise features by high pass filters. Based on the CW-HPF, a self-attention mechanism, called forgery attention, is proposed to capture rich contextual dependencies of intrinsic inconsistency extracted from tampered regions. Specifically, we append two types of attention modules on top of CW-HPF respectively to model internal interdependencies in spatial dimension and external dependencies among channels. We exploit a coarse-to-fine network to enhance the noise inconsistency between original and tampered regions. More importantly, to address the issue of insufficient training data, we design a self-adversarial training strategy that expands training data dynamically to achieve more robust performance. Specifically, in each training iteration, we perform adversarial attacks against our network to generate adversarial examples and train our model on them. Extensive experimental results demonstrate that our proposed algorithm steadily outperforms state-of-the-art methods by a clear margin in different benchmark datasets.