Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

• URL: http://arxiv.org/abs/2002.01008v3
• Date: Sun, 9 Aug 2020 18:23:24 GMT
• Title: Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
• Authors: Zhengyu Zhao, Zhuoran Liu, Martha Larson
• Abstract summary: We introduce an approach that enhances images using a color filter in order to create adversarial effects, which fool neural networks into misclassification. Our approach, Adversarial Color Enhancement (ACE), generates unrestricted adversarial images by optimizing the color filter via gradient descent.
• Score: 5.682107851677069
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce an approach that enhances images using a color filter in order to create adversarial effects, which fool neural networks into misclassification. Our approach, Adversarial Color Enhancement (ACE), generates unrestricted adversarial images by optimizing the color filter via gradient descent. The novelty of ACE is its incorporation of established practice for image enhancement in a transparent manner. Experimental results validate the white-box adversarial strength and black-box transferability of ACE. A range of examples demonstrates the perceptual quality of images that ACE produces. ACE makes an important contribution to recent work that moves beyond $L_p$ imperceptibility and focuses on unrestricted adversarial modifications that yield large perceptible perturbations, but remain non-suspicious, to the human eye. The future potential of filter-based adversaries is also explored in two directions: guiding ACE with common enhancement practices (e.g., Instagram filters) towards specific attractive image styles and adapting ACE to image semantics. Code is available at https://github.com/ZhengyuZhao/ACE.

Related papers

• ACE: Anti-Editing Concept Erasure in Text-to-Image Models [73.00930293474009]
  Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts. We propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing.
  arXiv  Detail & Related papers  (2025-01-03T04:57:27Z)
• Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack [51.16384207202798]
  Vision-language pre-training models are vulnerable to multimodal adversarial examples (AEs) Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process. We propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity.
  arXiv  Detail & Related papers  (2024-11-04T23:07:51Z)
• Multiple Latent Space Mapping for Compressed Dark Image Enhancement [51.112925890246444]
  Existing dark image enhancement methods take compressed dark images as inputs and achieve great performance. We propose a novel latent mapping network based on variational auto-encoder (VAE) Comprehensive experiments demonstrate that the proposed method achieves state-of-the-art performance in compressed dark image enhancement.
  arXiv  Detail & Related papers  (2024-03-12T13:05:51Z)
• Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search [98.2559247611821]
  We present a novel deep intra-image contrastive learning using a Siamese network. Our method achieves a state-of-the-art performance among weakly supervised one-step person search approaches.
  arXiv  Detail & Related papers  (2023-02-09T12:45:20Z)
• Towards Vivid and Diverse Image Colorization with Generative Color Prior [17.087464490162073]
  Recent deep-learning-based methods could automatically colorize images at a low cost. We aim at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN) Thanks to the powerful generative color prior and delicate designs, our method could produce vivid colors with a single forward pass.
  arXiv  Detail & Related papers  (2021-08-19T17:49:21Z)
• Enhancing Underwater Image via Adaptive Color and Contrast Enhancement, and Denoising [2.298932494750101]
  We propose an adaptive color and contrast enhancement, and denoising (ACCE-D) framework for underwater image enhancement. We derive a numerical solution for ACCE, and adopt a pyramid-based strategy to accelerate the solving procedure. Experimental results demonstrate that our strategy is effective in color correction, visibility improvement, and detail revealing.
  arXiv  Detail & Related papers  (2021-04-02T14:37:20Z)
• Error Diffusion Halftoning Against Adversarial Examples [85.11649974840758]
  Adversarial examples contain carefully crafted perturbations that can fool deep neural networks into making wrong predictions. We propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples.
  arXiv  Detail & Related papers  (2021-01-23T07:55:02Z)
• Essential Features: Reducing the Attack Surface of Adversarial Perturbations with Robust Content-Aware Image Preprocessing [5.831840281853604]
  Adversaries can fool machine learning models into making incorrect predictions by adding perturbations to an image. One approach to defending against such perturbations is to apply image preprocessing functions to remove the effects of the perturbation. We propose a novel image preprocessing technique called Essential Features that transforms the image into a robust feature space.
  arXiv  Detail & Related papers  (2020-12-03T04:40:51Z)
• Adversarial Image Color Transformations in Explicit Color Filter Space [5.682107851677069]
  Adversarial Color Filter (AdvCF) is a novel color transformation attack that is optimized with gradient information in the parameter space of a simple color filter. We show that AdvCF is superior over the state-of-the-art human-interpretable color transformation attack on both image acceptability and efficiency.
  arXiv  Detail & Related papers  (2020-11-12T23:51:37Z)
• Boosting Gradient for White-Box Adversarial Attacks [60.422511092730026]
  We propose a universal adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient based white-box attack algorithms. Our approach calculates the gradient of the loss function versus network input, maps the values to scores, and selects a part of them to update the misleading gradients.
  arXiv  Detail & Related papers  (2020-10-21T02:13:26Z)
• Color and Edge-Aware Adversarial Image Perturbations [0.0]
  We develop two new methods for constructing adversarial perturbations. The Edge-Aware method reduces the magnitude of perturbations permitted in smooth regions of an image. The Color-Aware and Edge-Aware methods can also be implemented simultaneously.
  arXiv  Detail & Related papers  (2020-08-28T03:02:20Z)
• Creating Artificial Modalities to Solve RGB Liveness [79.9255035557979]
  We introduce two types of artificial transforms: rank pooling and optical flow, combined in end-to-end pipeline for spoof detection. The proposed method achieves state-of-the-art on the largest cross-ethnicity face anti-spoofing dataset CASIA-SURF CeFA (RGB)
  arXiv  Detail & Related papers  (2020-06-29T13:19:22Z)

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.