MetaCloak-JPEG: JPEG-Robust Adversarial Perturbation for Preventing Unauthorized DreamBooth-Based Deepfake Generation

• URL: http://arxiv.org/abs/2604.18537v1
• Date: Mon, 20 Apr 2026 17:32:48 GMT
• Title: MetaCloak-JPEG: JPEG-Robust Adversarial Perturbation for Preventing Unauthorized DreamBooth-Based Deepfake Generation
• Abstract summary: PhotoGuard, Anti-DreamBooth, and MetaCloak perturb user images to disrupt surrogate fine-tuning.<n>None backpropagates gradients through the JPEG compression pipeline.<n> Diff is embedded in a JPEG-aware EOT.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid progress of subject-driven text-to-image synthesis, and in particular DreamBooth, has enabled a consent-free deepfake pipeline: an adversary needs only 4-8 publicly available face images to fine-tune a personalized diffusion model and produce photorealistic harmful content. Current adversarial face-protection systems -- PhotoGuard, Anti-DreamBooth, and MetaCloak -- perturb user images to disrupt surrogate fine-tuning, but all share a structural blindness: none backpropagates gradients through the JPEG compression pipeline that every major social-media platform applies before adversary access. Because JPEG quantization relies on round(), whose derivative is zero almost everywhere, adversarial energy concentrates in high-frequency DCT bands that JPEG discards, eliminating 60-80% of the protective signal. We introduce MetaCloak-JPEG, which closes this gap by inserting a Differentiable JPEG (DiffJPEG) layer built on the Straight-Through Estimator (STE): the forward pass applies standard JPEG compression, while the backward pass replaces round() with the identity. DiffJPEG is embedded in a JPEG-aware EOT distribution (~70% of augmentations include DiffJPEG) and a curriculum quality-factor schedule (QF: 95 to 50) inside a bilevel meta-learning loop. Under an l-inf perturbation budget of eps=8/255, MetaCloak-JPEG attains 32.7 dB PSNR, a 91.3% JPEG survival rate, and outperforms PhotoGuard on all 9 evaluated JPEG quality factors (9/9 wins, mean denoising-loss gain +0.125) within a 4.1 GB training-memory budget.

Related papers

• Learned JPEG Compression for DNN Vision [15.86593426643386]
  In the era of artificial intelligence (AI), a substantial portion of image data, often compressed by JPEG, is and will continue to be consumed by deep neural networks (DNNs) instead of humans.<n>We propose learned JPEG compression for DNN vision (J4D), a novel training framework for determining JPEG encoding parameters to minimize compression rate while maximizing inference performance.
  arXiv  Detail & Related papers  (2026-06-15T03:56:45Z)
• JPEG Inspired Deep Learning [4.958744940097937]
  Well-crafted JPEG compression can actually improve the performance of deep learning (DL)<n>We propose JPEG-DL, a novel DL framework that prepends any underlying DNN architecture with a trainable JPEG compression layer.<n>Our code is available on https://github.com/AhmedHussKhalifa/Inspired-DL.git.
  arXiv  Detail & Related papers  (2024-10-09T17:23:54Z)
• Unified learning-based lossy and lossless JPEG recompression [15.922937139019547]
  We propose a unified lossly and lossless JPEG recompression framework, which consists of learned quantization table and Markovian hierarchical variational autoencoders. Experiments show that our method can achieve arbitrarily low distortion when the JPEG is close to the upper bound.
  arXiv  Detail & Related papers  (2023-12-05T12:07:27Z)
• Differentiable JPEG: The Devil is in the Details [2.246961121930528]
  We propose a novel diff. JPEG approach, overcoming previous limitations. Our approach is differentiable w.r.t. the input image, the JPEG quality, the quantization tables, and the color conversion parameters. Our proposed diff. JPEG resembles the (non-diff.) reference implementation best, significantly surpassing the recent-best diff. approach by $3.47$dB (PSNR) on average.
  arXiv  Detail & Related papers  (2023-09-13T14:13:08Z)
• Learned Lossless Compression for JPEG via Frequency-Domain Prediction [50.20577108662153]
  We propose a novel framework for learned lossless compression of JPEG images. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An autoencoder-like architecture is designed based on the weight-shared blocks to realize entropy modeling of grouped DCT coefficients.
  arXiv  Detail & Related papers  (2023-03-05T13:15:28Z)
• Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain [10.655855413391324]
  We propose a deep learning based JPEG recompression method that operates on DCT domain. Experiments show that our method achieves state-of-the-art performance compared with traditional JPEG recompression methods.
  arXiv  Detail & Related papers  (2022-03-30T14:36:13Z)
• Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder [73.48927855855219]
  We propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends. Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics.
  arXiv  Detail & Related papers  (2022-01-27T20:20:03Z)
• Towards Flexible Blind JPEG Artifacts Removal [73.46374658847675]
  We propose a flexible blind convolutional neural network, namely FBCNN, that can predict the adjustable quality factor to control the trade-off between artifacts removal and details preservation. Our proposed FBCNN achieves favorable performance against state-of-the-art methods in terms of both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2021-09-29T17:12:10Z)
• Improving Cost Learning for JPEG Steganography by Exploiting JPEG Domain Knowledge [52.880912557105106]
  JEC-RL is explicitly designed to tailor the JPEG DCT structure. It works with the embedding action sampling mechanism under reinforcement learning. It can achieve good security performance for JPEG images against both advanced feature based and modern CNN based steganalyzers.
  arXiv  Detail & Related papers  (2021-05-09T08:10:41Z)
• Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach [78.05383266222285]
  It is still an open challenge to achieve the goal of data hiding that can be against these compressions. Deep learning has shown large success in data hiding, while non-differentiability of JPEG makes it challenging to train a deep pipeline for improving robustness against lossy compression. In this work, we propose a simple yet effective approach to address all the above limitations at once.
  arXiv  Detail & Related papers  (2020-12-30T12:30:09Z)
• Learning to Improve Image Compression without Changing the Standard Decoder [100.32492297717056]
  We propose learning to improve the encoding performance with the standard decoder. Specifically, a frequency-domain pre-editing method is proposed to optimize the distribution of DCT coefficients. We do not modify the JPEG decoder and therefore our approach is applicable when viewing images with the widely used standard JPEG decoder.
  arXiv  Detail & Related papers  (2020-09-27T19:24:42Z)

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.