SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning

• URL: http://arxiv.org/abs/2604.03833v1
• Date: Sat, 04 Apr 2026 19:19:33 GMT
• Title: SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning
• Abstract summary: SPARK-IL is a retrieval-augmented framework that combines dual-path spectral analysis with incremental learning.<n> evaluated on the UniversalFakeDetect benchmark across 19 generative models.
• Score: 6.901244434385347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting AI-generated images remains a significant challenge because detectors trained on specific generators often fail to generalize to unseen models; however, while pixel-level artifacts vary across models, frequency-domain signatures exhibit greater consistency, providing a promising foundation for cross-generator detection. To address this, we propose SPARK-IL, a retrieval-augmented framework that combines dual-path spectral analysis with incremental learning by utilizing a partially frozen ViT-L/14 encoder for semantic representations alongside a parallel path for raw RGB pixel embeddings. Both paths undergo multi-band Fourier decomposition into four frequency bands, which are individually processed by Kolmogorov-Arnold Networks (KAN) with mixture-of-experts for band-specific transformations before the resulting spectral embeddings are fused via cross-attention with residual connections. During inference, this fused embedding retrieves the $k$ nearest labeled signatures from a Milvus database using cosine similarity to facilitate predictions via majority voting, while an incremental learning strategy expands the database and employs elastic weight consolidation to preserve previously learned transformations. Evaluated on the UniversalFakeDetect benchmark across 19 generative models -- including GANs, face-swapping, and diffusion methods -- SPARK-IL achieves a 94.6\% mean accuracy, with the code to be publicly released at https://github.com/HessenUPHF/SPARK-IL.

Related papers

• PE-Mamba: Bidirectional Selective Layer Aggregation for AI-Generated Image Detection [2.1410799064827235]
  textbfPE-Mamba is a novel framework built upon a pre-trained PE-Core vision transformer with lightweight LoRA adaptation.<n>A bidirectional selective aggregator (BSA) processes layer-wise classification tokens through forward and backward selective scans.<n>A softmax-weighted aggregator (SWA) computes a learned global summary of all layer tokens as a complementary aggregation path.<n>A sigmoid-gated blend (SGA) adaptively fuses the BSA and SWA outputs via a learnable scalar gate.
  arXiv  Detail & Related papers  (2026-08-08T08:24:44Z)
• Full spectrum Unlearnable Examples via Spectral Equalization [29.22443621401928]
  We propose Full-spectrum Unlearnable examples via Spectral Equalization (FUSE)<n>FUSE generates spectrum-agnostic perturbations by equalizing the contributions from different bands and enforcing cross-band consistency.<n>Experiments across multiple datasets, architectures, and spectral filtering demonstrate the strong protection achieved by FUSE.
  arXiv  Detail & Related papers  (2026-06-25T07:53:53Z)
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram [6.62414474989199]
  We introduce a fuzzy clustering framework in the spectral domain to extract frequency-specific monotonic relationships across variables.<n>Our method takes advantage of dominant frequency-based cross-regional connectivity patterns to improve clustering accuracy.<n>As a flagship application, we analyze electroencephalogram recordings, where our approach uncovers frequency- and connectivity-specific markers of latent cognitive states.
  arXiv  Detail & Related papers  (2025-06-28T12:02:01Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Any-Resolution AI-Generated Image Detection by Spectral Learning [36.562914181733426]
  We build upon the key idea that the spectral distribution of real images constitutes both an invariant and highly discriminative pattern for AI-generated image detection.<n>Our approach achieves a 5.5% absolute improvement in AUC over the previous state-of-the-art across 13 recent generative approaches.
  arXiv  Detail & Related papers  (2024-11-28T23:55:19Z)
• Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection [0.0]
  Wavelet-CLIP is a deepfake detection framework that integrates wavelet transforms with features derived from the ViT-L/14 architecture, pre-trained in the CLIP fashion.<n>Our method showcases outstanding performance, achieving an average AUC of 0.749 for cross-data generalization and 0.893 for robustness against unseen deepfakes.
  arXiv  Detail & Related papers  (2024-09-26T21:16:51Z)
• Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
  We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network. Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
  arXiv  Detail & Related papers  (2024-08-28T10:07:17Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction [138.04956118993934]
  We propose a novel Transformer-based method, coarse-to-fine sparse Transformer (CST) CST embedding HSI sparsity into deep learning for HSI reconstruction. In particular, CST uses our proposed spectra-aware screening mechanism (SASM) for coarse patch selecting. Then the selected patches are fed into our customized spectra-aggregation hashing multi-head self-attention (SAH-MSA) for fine pixel clustering and self-similarity capturing.
  arXiv  Detail & Related papers  (2022-03-09T16:17:47Z)
• Generalizing Face Forgery Detection with High-frequency Features [63.33397573649408]
  Current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. We propose to utilize the high-frequency noises for face forgery detection. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective.
  arXiv  Detail & Related papers  (2021-03-23T08:19:21Z)

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.