# Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

Source: [Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models](<https://www.sota2.com/research/paper/68fa71401e209131cea501b0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:01:40.608Z

Authors: Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, Changick Kim

Published: 2023-11-17T07:39:42.000Z

## Abstract

As video analysis using deep learning models becomes more widespread, the vulnerability of such models to adversarial attacks is becoming a pressing concern. In particular, Universal Adversarial Perturbation (UAP) poses a significant threat, as a single perturbation can mislead deep learning models on entire datasets. We propose a novel video UAP using image data and image model. This enables us to take advantage of the rich image data and image model-based studies available for video applications. However, there is a challenge that image models are limited in their ability to analyze the temporal aspects of videos, which is crucial for a successful video attack. To address this challenge, we introduce the Breaking Temporal Consistency (BTC) method, which is the first attempt to incorporate temporal information into video attacks using image models. We aim to generate adversarial videos that have opposite patterns to the original. Specifically, BTC-UAP minimizes the feature similarity between neighboring frames in videos. Our approach is simple but effective at attacking unseen video models. Additionally, it is applicable to videos of varying lengths and invariant to temporal shifts. Our approach surpasses existing methods in terms of effectiveness on various datasets, including ImageNet, UCF-101, and Kinetics-400.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.10366>)

[PDF](<https://arxiv.org/pdf/2311.10366.pdf>)
