SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits

• URL: http://arxiv.org/abs/2604.10522v1
• Date: Sun, 12 Apr 2026 08:27:17 GMT
• Title: SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits
• Abstract summary: Sequential Editing in Diffusion (textbfSEED) is a large-scale benchmark for sequential tracing in facial imagery.<n>SEED contains over 90K images constructed via one to four sequential edits using diffusion-based editing pipelines.<n>SEED supports step-wise evidence analysis and support forgery detection, sequence prediction.
• Score: 22.00097357292037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deepfake content on social networks is increasingly produced through multiple \emph{sequential} edits to biometric data such as facial imagery. Consequently, the final appearance of an image often reflects a latent chain of operations rather than a single manipulation. Recovering these editing histories is essential for visual provenance analysis, misinformation auditing, and forensic or platform moderation workflows that must trace the origin and evolution of AI-generated media. However, existing datasets predominantly focus on single-step editing and overlook the cumulative artifacts introduced by realistic multi-step pipelines. To address this gap, we introduce Sequential Editing in Diffusion (\textbf{SEED}), a large-scale benchmark for sequential provenance tracing in facial imagery. SEED contains over 90K images constructed via one to four sequential attribute edits using diffusion-based editing pipelines, with fine-grained annotations including edit order, textual instructions, manipulation masks, and generation models. These metadata enable step-wise evidence analysis and support forgery detection, sequence prediction. To benchmark the challenges posed by SEED, we evaluate representative analysis strategies and observe that spatial-only approaches struggle under subtle and distributed diffusion artifacts, especially when such artifacts accumulate across multiple edits. Motivated by this observation, we further establish \textbf{FAITH}, a frequency-aware Transformer baseline that aggregates spatial and frequency-domain cues to identify and order latent editing events. Results show that high-frequency signals, particularly wavelet components, provide effective cues even under image degradation. Overall, SEED facilitates systematic study of sequential provenance tracing and evidence aggregation for trustworthy analysis of AI-generated visual content.

Related papers

• SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection [0.0]
  The rapid proliferation of AI-generated images (AIGI) presents a significant challenge to digital information integrity.<n>This paper introduces SPECTRA-Net, a scalable pipeline for explainable, cross-domain tensor representations for AIGI detection.
  arXiv  Detail & Related papers  (2026-05-06T16:35:47Z)
• SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation [39.55678505740112]
  We present the Surveillance Forgery Image Test Range (SurFITR)<n>SurFITR is a dataset for surveillance-style image forgery detection and localisation.<n>It contains over 137k tampered images with varying resolutions and edit types.
  arXiv  Detail & Related papers  (2026-04-08T13:55:02Z)
• Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection [53.789057575175065]
  Region-Aware Prompt Augmentation (RAPTA) and Attention-Driven Multimodal Copy Detection (ADMCD) are presented.<n>RAPTA uses an object detector to find salient regions and turn them into semantically grounded prompt variants.<n>ADMCD aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation.<n>Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
  arXiv  Detail & Related papers  (2026-03-13T15:16:27Z)
• RAID: Retrieval-Augmented Anomaly Detection [67.48358323718817]
  RAID is a retrieval-augmented UAD framework designed for noise-resilient anomaly detection and localization.<n> RAID retrieves class-, semantic-, and instance-level representations from a hierarchical vector database.<n> RAID achieves state-of-the-art performance across full-shot, few-shot, and multi-dataset settings on MVTec, VisA, MPDD, and BTAD benchmarks.
  arXiv  Detail & Related papers  (2026-02-23T08:54:27Z)
• DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection [48.00148913303519]
  Diffusion-based editing enables realistic modification of local image regions, making AI-generated content harder to detect.<n>We introduce DiffSeg30k, a dataset of 30k diffusion-edited images with pixel-level annotations to support fine-grained detection.
  arXiv  Detail & Related papers  (2025-11-24T13:43:54Z)
• Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations [56.816929931908824]
  We pioneer the detection of semantically-coordinated manipulations in multimodal data.<n>We propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework.<n>Our framework significantly outperforms existing methods, achieving 2.06% higher detection accuracy on SAMM compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-09-16T04:18:48Z)
• SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Models [23.54274625549125]
  A growing class of applications now demands the ability to analyze and track sequences of progressive edits.<n>We introduce SEED, a large-scale Sequentially Edited facE dataset constructed via state-of-the-art diffusion models.<n>SEED contains over 90,000 facial images with one to four sequential attribute modifications, generated using diverse diffusion-based editing pipelines.
  arXiv  Detail & Related papers  (2025-05-31T13:39:45Z)
• X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Models [3.610796534465868]
  Experimental results demonstrate that X-Edit accurately localizes edits in images altered by text-guided diffusion models.<n>This highlights X-Edit's potential as a robust forensic tool for detecting and pinpointing manipulations introduced by advanced image editing techniques.
  arXiv  Detail & Related papers  (2025-05-16T23:29:38Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)
• LIME: Localized Image Editing via Attention Regularization in Diffusion Models [69.33072075580483]
  This paper introduces LIME for localized image editing in diffusion models.<n>LIME does not require user-specified regions of interest (RoI) or additional text input, but rather employs features from pre-trained methods and a straightforward clustering method to obtain precise editing mask.<n>We propose a novel cross-attention regularization technique that penalizes unrelated cross-attention scores in the RoI during the denoising steps, ensuring localized edits.
  arXiv  Detail & Related papers  (2023-12-14T18:59:59Z)
• iEdit: Localised Text-guided Image Editing with Weak Supervision [53.082196061014734]
  We propose a novel learning method for text-guided image editing. It generates images conditioned on a source image and a textual edit prompt. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
  arXiv  Detail & Related papers  (2023-05-10T07:39:14Z)

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.