LipSim: A Provably Robust Perceptual Similarity Metric

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ghazanfari, Sara, Araujo, Alexandre, Krishnamurthy, Prashanth, Khorrami, Farshad, Garg, Siddharth
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917625576030208
author Ghazanfari, Sara
Araujo, Alexandre
Krishnamurthy, Prashanth
Khorrami, Farshad
Garg, Siddharth
author_facet Ghazanfari, Sara
Araujo, Alexandre
Krishnamurthy, Prashanth
Khorrami, Farshad
Garg, Siddharth
contents Recent years have seen growing interest in developing and applying perceptual similarity metrics. Research has shown the superiority of perceptual metrics over pixel-wise metrics in aligning with human perception and serving as a proxy for the human visual system. On the other hand, as perceptual metrics rely on neural networks, there is a growing concern regarding their resilience, given the established vulnerability of neural networks to adversarial attacks. It is indeed logical to infer that perceptual metrics may inherit both the strengths and shortcomings of neural networks. In this work, we demonstrate the vulnerability of state-of-the-art perceptual similarity metrics based on an ensemble of ViT-based feature extractors to adversarial attacks. We then propose a framework to train a robust perceptual similarity metric called LipSim (Lipschitz Similarity Metric) with provable guarantees. By leveraging 1-Lipschitz neural networks as the backbone, LipSim provides guarded areas around each data point and certificates for all perturbations within an $\ell_2$ ball. Finally, a comprehensive set of experiments shows the performance of LipSim in terms of natural and certified scores and on the image retrieval application. The code is available at https://github.com/SaraGhazanfari/LipSim.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18274
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LipSim: A Provably Robust Perceptual Similarity Metric
Ghazanfari, Sara
Araujo, Alexandre
Krishnamurthy, Prashanth
Khorrami, Farshad
Garg, Siddharth
Computer Vision and Pattern Recognition
Machine Learning
Recent years have seen growing interest in developing and applying perceptual similarity metrics. Research has shown the superiority of perceptual metrics over pixel-wise metrics in aligning with human perception and serving as a proxy for the human visual system. On the other hand, as perceptual metrics rely on neural networks, there is a growing concern regarding their resilience, given the established vulnerability of neural networks to adversarial attacks. It is indeed logical to infer that perceptual metrics may inherit both the strengths and shortcomings of neural networks. In this work, we demonstrate the vulnerability of state-of-the-art perceptual similarity metrics based on an ensemble of ViT-based feature extractors to adversarial attacks. We then propose a framework to train a robust perceptual similarity metric called LipSim (Lipschitz Similarity Metric) with provable guarantees. By leveraging 1-Lipschitz neural networks as the backbone, LipSim provides guarded areas around each data point and certificates for all perturbations within an $\ell_2$ ball. Finally, a comprehensive set of experiments shows the performance of LipSim in terms of natural and certified scores and on the image retrieval application. The code is available at https://github.com/SaraGhazanfari/LipSim.
title LipSim: A Provably Robust Perceptual Similarity Metric
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2310.18274