# Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment

arXiv: https://arxiv.org/abs/2602.15903 · HTML: https://mlsanity.com/paper/2602.15903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 56 of its 79 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Builds on (most cited first, 30 of 56)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding](https://mlsanity.com/paper/2311.11810/) (2023)
- [MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering](https://mlsanity.com/paper/2405.11985/) (2024)
- [Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.04187/) (2024)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting](https://mlsanity.com/paper/2505.14059/) (2025)
- [UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding](https://mlsanity.com/paper/2308.11592/) (2023)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy](https://mlsanity.com/paper/2406.01326/) (2024)
- [SPTS v2: Single-Point Scene Text Spotting](https://mlsanity.com/paper/2301.01635/) (2023)
- [Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection](https://mlsanity.com/paper/2203.15221/) (2022)
- [Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance](https://mlsanity.com/paper/2412.12974/) (2024)
- [TextSquare: Scaling up Text-Centric Visual Instruction Tuning](https://mlsanity.com/paper/2404.12803/) (2024)

## Abstract (arXiv)

The proliferation of highly realistic facial forgeries necessitates robust detection methods. However, existing approaches often suffer from limited accuracy and poor generalization due to significant distribution shifts among samples generated by diverse forgery techniques. To address these challenges, we propose a novel Multivariate and Soft Blending Augmentation with CLIP-guided Forgery Intensity Estimation (MSBA-CLIP) framework. Our method leverages the multimodal alignment capabilities of CLIP to capture subtle forgery traces. We introduce a Multivariate and Soft Blending Augmentation (MSBA) strategy that synthesizes images by blending forgeries from multiple methods with random weights, forcing the model to learn generalizable patterns. Furthermore, a dedicated Multivariate Forgery Intensity Estimation (MFIE) module is designed to explicitly guide the model in learning features related to varied forgery modes and intensities. Extensive experiments demonstrate state-of-the-art performance. On in-domain tests, our method improves Accuracy and AUC by 3.32% and 4.02%, respectively, over the best baseline. In cross-domain evaluations across five datasets, it achieves an average AUC gain of 3.27%. Ablation studies confirm the efficacy of both proposed components. While the reliance on a large vision-language model entails higher computational cost, our work presents a significant step towards more generalizable and robust deepfake detection.