Adversarial purification for no-reference image-quality metrics: applicability study and new methods

• URL: http://arxiv.org/abs/2404.06957v1
• Date: Wed, 10 Apr 2024 12:17:25 GMT
• Title: Adversarial purification for no-reference image-quality metrics: applicability study and new methods
• Authors: Aleksandr Gushchin, Anna Chistyakova, Vladislav Minashkin, Anastasia Antsiferova, Dmitriy Vatolin,
• Abstract summary: In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, compression, denoising, and modern neural network-based methods.
• Score: 41.95502426953125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial purification defences from image classifiers to IQA methods. In this paper, we apply several widespread attacks on IQA models and examine the success of the defences against them. The purification methodologies covered different preprocessing techniques, including geometrical transformations, compression, denoising, and modern neural network-based methods. Also, we address the challenge of assessing the efficacy of a defensive methodology by proposing ways to estimate output visual quality and the success of neutralizing attacks. Defences were tested against attack on three IQA metrics -- Linearity, MetaIQA and SPAQ. The code for attacks and defences is available at: (link is hidden for a blind review).

Related papers

• Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics [35.87448891459325]
  This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial attacks on IQA. We evaluate 25 defense strategies, including adversarial purification, adversarial training, and certified robustness methods. We analyze the differences between defenses and their applicability to IQA tasks, considering that they should preserve IQA scores and image quality.
  arXiv  Detail & Related papers  (2024-08-02T19:02:49Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• A Random-patch based Defense Strategy Against Physical Attacks for Face Recognition Systems [3.6202815454709536]
  We propose a random-patch based defense strategy to robustly detect physical attacks for Face Recognition System (FRS) Our method can be easily applied to the real world face recognition system and extended to other defense methods to boost the detection performance.
  arXiv  Detail & Related papers  (2023-04-16T16:11:56Z)
• Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey [114.17568992164303]
  Adrial attacks and defenses in machine learning and deep neural network have been gaining significant attention. This survey provides a comprehensive overview of the recent advancements in the field of adversarial attack and defense techniques. New avenues of attack are also explored, including search-based, decision-based, drop-based, and physical-world attacks.
  arXiv  Detail & Related papers  (2023-03-11T04:19:31Z)
• Attacking Face Recognition with T-shirts: Database, Vulnerability Assessment and Detection [0.0]
  We propose a new T-shirt Face Presentation Attack database of 1,608 T-shirt attacks using 100 unique presentation attack instruments. We show that this type of attack can compromise the security of face recognition systems and that some state-of-the-art attack detection mechanisms fail to robustly generalize to the new attacks.
  arXiv  Detail & Related papers  (2022-11-14T14:11:23Z)
• Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution [83.84968082791444]
  Deep neural networks are vulnerable to intentionally crafted adversarial examples. Various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models.
  arXiv  Detail & Related papers  (2021-08-29T08:11:36Z)
• A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning [122.49765136434353]
  We present an effective method, called Hamiltonian Monte Carlo with Accumulated Momentum (HMCAM), aiming to generate a sequence of adversarial examples. We also propose a new generative method called Contrastive Adversarial Training (CAT), which approaches equilibrium distribution of adversarial examples. Both quantitative and qualitative analysis on several natural image datasets and practical systems have confirmed the superiority of the proposed algorithm.
  arXiv  Detail & Related papers  (2020-10-15T16:07:26Z)
• Adversarial Attacks against Face Recognition: A Comprehensive Study [3.766020696203255]
  Face recognition (FR) systems have demonstrated outstanding verification performance. Recent studies show that (deep) FR systems exhibit an intriguing vulnerability to imperceptible or perceptible but natural-looking adversarial input images.
  arXiv  Detail & Related papers  (2020-07-22T22:46:00Z)
• Towards Transferable Adversarial Attack against Deep Face Recognition [58.07786010689529]
  Deep convolutional neural networks (DCNNs) have been found to be vulnerable to adversarial examples. transferable adversarial examples can severely hinder the robustness of DCNNs. We propose DFANet, a dropout-based method used in convolutional layers, which can increase the diversity of surrogate models. We generate a new set of adversarial face pairs that can successfully attack four commercial APIs without any queries.
  arXiv  Detail & Related papers  (2020-04-13T06:44:33Z)

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.