# SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints

arXiv: https://arxiv.org/abs/2412.09981 · HTML: https://mlsanity.com/paper/2412.09981/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 36 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 1 of 1)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)

## Built on by (most cited first, 5 of 5)

- [A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localization](https://mlsanity.com/paper/2507.16596/) (2025)
- [AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era](https://mlsanity.com/paper/2504.11015/) (2025)
- [Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework](https://mlsanity.com/paper/2508.01338/) (2025)
- [Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation](https://mlsanity.com/paper/2508.20987/) (2025)
- [Towards Open-world Generalized Deepfake Detection: General Feature Extraction via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2505.12339/) (2025)

## Abstract (arXiv)

Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety. However, due to the rapid development of image tampering technologies, extracting more comprehensive and accurate forgery clues remains an urgent challenge. To address these challenges, we introduce a novel information-theoretic IFL framework named SUMI-IFL that imposes sufficiency-view and minimality-view constraints on forgery feature representation. First, grounded in the theoretical analysis of mutual information, the sufficiency-view constraint is enforced on the feature extraction network to ensure that the latent forgery feature contains comprehensive forgery clues. Considering that forgery clues obtained from a single aspect alone may be incomplete, we construct the latent forgery feature by integrating several individual forgery features from multiple perspectives. Second, based on the information bottleneck, the minimality-view constraint is imposed on the feature reasoning network to achieve an accurate and concise forgery feature representation that counters the interference of task-unrelated features. Extensive experiments show the superior performance of SUMI-IFL to existing state-of-the-art methods, not only on in-dataset comparisons but also on cross-dataset comparisons.