Pith. sign in

REVIEW 2 cited by

Attacking Perceptual Similarity Metrics

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.08840 v1 pith:C54S6JAM submitted 2023-05-15 cs.CV eess.IV

classification cs.CVeess.IV
keywords metricsadversarialattackperturbationssimilarityimperceptibleperceptualrobustness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion can still compromise these metrics. In our study, we systematically examine the robustness of these metrics to imperceptible adversarial perturbations. Following the two-alternative forced-choice experimental design with two distorted images and one reference image, we perturb the distorted image closer to the reference via an adversarial attack until the metric flips its judgment. We first show that all metrics in our study are susceptible to perturbations generated via common adversarial attacks such as FGSM, PGD, and the One-pixel attack. Next, we attack the widely adopted LPIPS metric using spatial-transformation-based adversarial perturbations (stAdv) in a white-box setting to craft adversarial examples that can effectively transfer to other similarity metrics in a black-box setting. We also combine the spatial attack stAdv with PGD ($\ell_\infty$-bounded) attack to increase transferability and use these adversarial examples to benchmark the robustness of both traditional and recently developed metrics. Our benchmark provides a good starting point for discussion and further research on the robustness of metrics to imperceptible adversarial perturbations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Removal Coherence (RC) metrics, which compare local feature distributions in masked versus background regions via sliding-window MMD, align with human judgments of object-removal quality substantially better than exis...

  2. Predicting Air Temperature from Volumetric Urban Morphology with Machine Learning

    cs.LG 2025-01 conditional novelty 5.0 of 10

    A machine learning model predicts 1km-resolution nighttime summer air temperature from building volumes derived from a new fast CityGML voxelization method, with Random Forest capturing spatial patterns better than XGBoost.

Pith tools