Related papers: IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics

IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics

URL: http://arxiv.org/abs/2403.05955v2
Date: Wed, 29 May 2024 19:56:36 GMT
Title: IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
Authors: Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin,
Abstract summary: No-reference image- and video-quality metrics are widely used in video processing benchmarks. This paper introduces an Invisible One-Iteration (IOI) adversarial attack on no reference image and video quality metrics.
Score: 4.135467749401761
License: http://creativecommons.org/licenses/by/4.0/
Abstract: No-reference image- and video-quality metrics are widely used in video processing benchmarks. The robustness of learning-based metrics under video attacks has not been widely studied. In addition to having success, attacks that can be employed in video processing benchmarks must be fast and imperceptible. This paper introduces an Invisible One-Iteration (IOI) adversarial attack on no reference image and video quality metrics. We compared our method alongside eight prior approaches using image and video datasets via objective and subjective tests. Our method exhibited superior visual quality across various attacked metric architectures while maintaining comparable attack success and speed. We made the code available on GitHub: https://github.com/katiashh/ioi-attack.

Related papers

Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics [3.7855740990304736]
No-reference image- and video-quality metrics are crucial in many computer vision tasks. The vulnerability of quality metrics imposes restrictions on using such metrics in quality control systems. This paper proposes a new method for testing quality metrics vulnerability in the physical space.
arXiv Detail & Related papers (2024-04-15T17:38:47Z)
Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks [43.85564498709518]
This paper analyses modern metrics' robustness to different adversarial attacks. Some metrics showed high resistance to adversarial attacks, which makes their usage in benchmarks safer than vulnerable metrics.
arXiv Detail & Related papers (2023-10-10T19:21:41Z)
Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics [0.0]
We propose a fast adversarial attack on no-reference quality metrics. The proposed attack can be exploited as a preprocessing step in real-time video processing and compression algorithms. This research can yield insights to further aid in designing of stable neural-network-based no-reference quality metrics.
arXiv Detail & Related papers (2023-05-24T20:18:21Z)
Video compression dataset and benchmark of learning-based video-quality metrics [55.41644538483948]
We present a new benchmark for video-quality metrics that evaluates video compression. It is based on a new dataset consisting of about 2,500 streams encoded using different standards. Subjective scores were collected using crowdsourced pairwise comparisons.
arXiv Detail & Related papers (2022-11-22T09:22:28Z)
Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics [0.0]
Some attacks can deceive image- and video-quality metrics. We propose a new method to attack differentiable no-reference quality metrics through universal perturbation.
arXiv Detail & Related papers (2022-11-01T10:28:13Z)
Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining [16.49278694957565]
State-of-the-art (SOTA) contrastive learning techniques consider frames within a video as positives in the embedding space. We observe that unlike multiple views of an object in natural scene videos, an Ultrasound (US) video captures different 2D slices of an organ. We propose to instead utilize such frames as hard negatives to learn rich image representations.
arXiv Detail & Related papers (2022-07-26T19:00:33Z)
Objective video quality metrics application to video codecs comparisons: choosing the best for subjective quality estimation [101.18253437732933]
Quality assessment plays a key role in creating and comparing video compression algorithms. For comparison, we used a set of videos encoded with video codecs of different standards, and visual quality scores collected for the resulting set of streams since 2018 until 2021.
arXiv Detail & Related papers (2021-07-21T17:18:11Z)
Semi-Supervised Action Recognition with Temporal Contrastive Learning [50.08957096801457]
We learn a two-pathway temporal contrastive model using unlabeled videos at two different speeds. We considerably outperform video extensions of sophisticated state-of-the-art semi-supervised image recognition methods.
arXiv Detail & Related papers (2021-02-04T17:28:35Z)
Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation [132.82884193921535]
We argue that previous methods underestimate the importance of video feature learning and propose a two-stage approach. We show that this simple baseline approach outperforms prior few-shot video classification methods by over 20 points on existing benchmarks. We present two novel approaches that yield further improvement.
arXiv Detail & Related papers (2020-07-09T13:05:32Z)
Watching the World Go By: Representation Learning from Unlabeled Videos [78.22211989028585]
Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. In this paper, we argue that videos offer this natural augmentation for free. We propose Video Noise Contrastive Estimation, a method for using unlabeled video to learn strong, transferable single image representations.
arXiv Detail & Related papers (2020-03-18T00:07:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.