Attack as Defense: Run-time Backdoor Implantation for Image Content Protection

• URL: http://arxiv.org/abs/2410.14966v1
• Date: Sat, 19 Oct 2024 03:58:25 GMT
• Title: Attack as Defense: Run-time Backdoor Implantation for Image Content Protection
• Authors: Haichuan Zhang, Meiyu Lin, Zhaoyi Liu, Renyuan Li, Zhiyuan Cheng, Carl Yang, Mingjie Tang,
• Abstract summary: A backdoor attack is a method that implants vulnerabilities in a target model, which can be activated through a trigger. In this work, we innovatively prevent the abuse of image content modification by implanting the backdoor into image-editing models. Unlike traditional backdoor attacks that use data poisoning, to enable protection on individual images, we developed the first framework for run-time backdoor implantation.
• Score: 20.30801340875602
• License:
• Abstract: As generative models achieve great success, tampering and modifying the sensitive image contents (i.e., human faces, artist signatures, commercial logos, etc.) have induced a significant threat with social impact. The backdoor attack is a method that implants vulnerabilities in a target model, which can be activated through a trigger. In this work, we innovatively prevent the abuse of image content modification by implanting the backdoor into image-editing models. Once the protected sensitive content on an image is modified by an editing model, the backdoor will be triggered, making the editing fail. Unlike traditional backdoor attacks that use data poisoning, to enable protection on individual images and eliminate the need for model training, we developed the first framework for run-time backdoor implantation, which is both time- and resource- efficient. We generate imperceptible perturbations on the images to inject the backdoor and define the protected area as the only backdoor trigger. Editing other unprotected insensitive areas will not trigger the backdoor, which minimizes the negative impact on legal image modifications. Evaluations with state-of-the-art image editing models show that our protective method can increase the CLIP-FID of generated images from 12.72 to 39.91, or reduce the SSIM from 0.503 to 0.167 when subjected to malicious editing. At the same time, our method exhibits minimal impact on benign editing, which demonstrates the efficacy of our proposed framework. The proposed run-time backdoor can also achieve effective protection on the latest diffusion models. Code are available.

Related papers

• Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing [19.94455452402954]
  FaceLock is a novel approach to portrait protection that optimize adversarial perturbations to destroy or significantly alter biometric information. Our work advances biometric defense and sets the foundation for privacy-preserving practices in image editing.
  arXiv  Detail & Related papers  (2024-11-25T18:59:03Z)
• Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models [68.40324627475499]
  We introduce a novel two-step defense framework named Expose Before You Defend. EBYD unifies existing backdoor defense methods into a comprehensive defense system with enhanced performance. We conduct extensive experiments on 10 image attacks and 6 text attacks across 2 vision datasets and 4 language datasets.
  arXiv  Detail & Related papers  (2024-10-25T09:36:04Z)
• PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacement [41.05432008027312]
  Online person re-identification services privacy breaches from potential data leakage recovery attacks. Previous privacy-preserving person re-identification methods are unable to resist recovery attacks and compromise accuracy. We propose an iterative (PixelFade) method to protect pedestrian images.
  arXiv  Detail & Related papers  (2024-08-10T12:52:54Z)
• Invisible Backdoor Attack Through Singular Value Decomposition [2.681558084723648]
  backdoor attacks pose a serious security threat to deep neural networks (DNNs) To make triggers less perceptible and imperceptible, various invisible backdoor attacks have been proposed. This paper proposes an invisible backdoor attack called DEBA.
  arXiv  Detail & Related papers  (2024-03-18T13:25:12Z)
• Backdoor Attack with Mode Mixture Latent Modification [26.720292228686446]
  We propose a backdoor attack paradigm that only requires minimal alterations to a clean model in order to inject the backdoor under the guise of fine-tuning. We evaluate the effectiveness of our method on four popular benchmark datasets.
  arXiv  Detail & Related papers  (2024-03-12T09:59:34Z)
• IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI [52.90082445349903]
  Diffusion-based image generation models can create artistic images that mimic the style of an artist or maliciously edit the original images for fake content. Several attempts have been made to protect the original images from such unauthorized data usage by adding imperceptible perturbations. In this work, we introduce a purification perturbation platform, named IMPRESS, to evaluate the effectiveness of imperceptible perturbations as a protective measure.
  arXiv  Detail & Related papers  (2023-10-30T03:33:41Z)
• Physical Invisible Backdoor Based on Camera Imaging [32.30547033643063]
  Current backdoor attacks require changing pixels of clean images. This paper proposes a novel physical invisible backdoor based on camera imaging without changing nature image pixels.
  arXiv  Detail & Related papers  (2023-09-14T04:58:06Z)
• PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow [69.78820726573935]
  We name it PRO-Face S, short for Privacy-preserving Reversible Obfuscation of Face images via Secure flow-based model. In the framework, an Invertible Neural Network (INN) is utilized to process the input image along with its pre-obfuscated form, and generate the privacy protected image that visually approximates to the pre-obfuscated one.
  arXiv  Detail & Related papers  (2023-07-18T10:55:54Z)
• DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection [64.77548539959501]
  DiffProtect produces more natural-looking encrypted images than state-of-the-art methods. It achieves significantly higher attack success rates, e.g., 24.5% and 25.1% absolute improvements on the CelebA-HQ and FFHQ datasets.
  arXiv  Detail & Related papers  (2023-05-23T02:45:49Z)
• Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder [57.739693628523]
  We propose a framework for blind backdoor defense with Masked AutoEncoder (BDMAE) BDMAE detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations. Our approach is blind to the model restorations, trigger patterns and image benignity.
  arXiv  Detail & Related papers  (2023-03-27T19:23:33Z)
• Backdoor Attack in the Physical World [49.64799477792172]
  Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs) Most existing backdoor attacks adopted the setting of static trigger, $i.e.,$ triggers across the training and testing images. We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
  arXiv  Detail & Related papers  (2021-04-06T08:37:33Z)

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.