Toward Adaptive Meta-Gradient Adversarial Examples for Visual Tracking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18470%2F25%3A50022607" target="_blank" >RIV/62690094:18470/25:50022607 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11051004" target="_blank" >https://ieeexplore.ieee.org/document/11051004</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TR.2025.3569828" target="_blank" >10.1109/TR.2025.3569828</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Toward Adaptive Meta-Gradient Adversarial Examples for Visual Tracking

Popis výsledku v původním jazyce

In recent years, visual tracking methods based on convolutional neural networks and transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multimodel ensemble and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets, such as OTB2015, LaSOT, and GOT-10 k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples.

Název v anglickém jazyce

Toward Adaptive Meta-Gradient Adversarial Examples for Visual Tracking

Popis výsledku anglicky

In recent years, visual tracking methods based on convolutional neural networks and transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multimodel ensemble and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets, such as OTB2015, LaSOT, and GOT-10 k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE TRANSACTIONS ON RELIABILITY

ISSN

0018-9529

e-ISSN

1558-1721

Svazek periodika

74

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

5205-5218

Kód UT WoS článku

001518846000001

EID výsledku v databázi Scopus

2-s2.0-105009380337