Explainable Deepfake Detection with RL Enhanced Self-Blended Images

• URL: http://arxiv.org/abs/2601.15624v1
• Date: Thu, 22 Jan 2026 03:55:46 GMT
• Title: Explainable Deepfake Detection with RL Enhanced Self-Blended Images
• Authors: Ning Jiang, Dingheng Zeng, Yanhong Liu, Haiyang Yi, Shijie Yu, Minghe Weng, Haifeng Shen, Ying Li,
• Abstract summary: We propose an automated Chain-of-Thought (CoT) data generation framework based on Self-Blended Images, along with an RL-enhanced deepfake detection framework.<n>Our method achieves performance competitive with state-of-the-art (SOTA) approaches across multiple cross-dataset benchmarks.
• Score: 13.456365650507877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most prior deepfake detection methods lack explainable outputs. With the growing interest in multimodal large language models (MLLMs), researchers have started exploring their use in interpretable deepfake detection. However, a major obstacle in applying MLLMs to this task is the scarcity of high-quality datasets with detailed forgery attribution annotations, as textual annotation is both costly and challenging - particularly for high-fidelity forged images or videos. Moreover, multiple studies have shown that reinforcement learning (RL) can substantially enhance performance in visual tasks, especially in improving cross-domain generalization. To facilitate the adoption of mainstream MLLM frameworks in deepfake detection with reduced annotation cost, and to investigate the potential of RL in this context, we propose an automated Chain-of-Thought (CoT) data generation framework based on Self-Blended Images, along with an RL-enhanced deepfake detection framework. Extensive experiments validate the effectiveness of our CoT data construction pipeline, tailored reward mechanism, and feedback-driven synthetic data generation approach. Our method achieves performance competitive with state-of-the-art (SOTA) approaches across multiple cross-dataset benchmarks. Implementation details are available at https://github.com/deon1219/rlsbi.

Related papers

• ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization [62.03035862528452]
  ForgeryVCR is a framework that materializes imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning.<n>ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks.
  arXiv  Detail & Related papers  (2026-02-15T11:14:47Z)
• LLM-Enhanced Reinforcement Learning for Time Series Anomaly Detection [1.1852406625172216]
  Time series anomaly detection often suffers from sparse labels, complex temporal patterns, and costly expert annotation.<n>We propose a unified framework that integrates Large Language Model (LLM)-based potential functions for reward shaping with Reinforcement Learning (RL), Variational Autoencoder (VAE)-enhanced dynamic reward scaling, and active learning with label propagation.
  arXiv  Detail & Related papers  (2026-01-05T19:33:30Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• Leveraging Mixture of Experts for Improved Speech Deepfake Detection [53.69740463004446]
  Speech deepfakes pose a significant threat to personal security and content authenticity. We introduce a novel approach for enhancing speech deepfake detection performance using a Mixture of Experts architecture.
  arXiv  Detail & Related papers  (2024-09-24T13:24:03Z)
• Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection [16.21235742118949]
  We propose a novel approach that repurposes a well-trained Vision-Language Models (VLMs) for general deepfake detection.<n>Motivated by the model reprogramming paradigm that manipulates the model prediction via input perturbations, our method can reprogram a pre-trained VLM model.<n>Experiments on several popular benchmark datasets demonstrate that the cross-dataset and cross-manipulation performances of deepfake detection can be significantly and consistently improved.
  arXiv  Detail & Related papers  (2024-09-04T12:46:30Z)
• PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network [24.54269823691119]
  We present an advanced study on more challenging high-resolution salient object detection (HRSOD) from both dataset and network framework perspectives. To compensate for the lack of HRSOD dataset, we thoughtfully collect a large-scale high resolution salient object detection dataset, called UHRSD. All the images are finely annotated in pixel-level, far exceeding previous low-resolution SOD datasets.
  arXiv  Detail & Related papers  (2024-08-02T09:31:21Z)
• Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model [16.69101880602321]
  We propose a novel side-network-based decoder for generalized video-based Deepfake detection.<n>We also introduce Facial Component Guidance (FCG) to enhance spatial learning generalizability.<n>Our approach demonstrates promising generalizability on challenging Deepfake datasets.
  arXiv  Detail & Related papers  (2024-04-08T14:58:52Z)
• Fus-MAE: A cross-attention-based data fusion approach for Masked Autoencoders in remote sensing [5.070981175240306]
  Fus-MAE is a self-supervised learning framework based on masked autoencoders.<n>Our empirical findings demonstrate that Fus-MAE can effectively compete with contrastive learning strategies tailored for SAR-optical data fusion.
  arXiv  Detail & Related papers  (2024-01-05T11:36:21Z)
• CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition [53.860796916196634]
  We propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF) Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. It adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination.
  arXiv  Detail & Related papers  (2023-09-30T12:30:25Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Learning Efficient Representations for Enhanced Object Detection on Large-scene SAR Images [16.602738933183865]
  It is a challenging problem to detect and recognize targets on complex large-scene Synthetic Aperture Radar (SAR) images. Recently developed deep learning algorithms can automatically learn the intrinsic features of SAR images. We propose an efficient and robust deep learning based target detection method.
  arXiv  Detail & Related papers  (2022-01-22T03:25:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.