Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Chiyu, Zhou, Lu, Xu, Xiaogang, Wu, Jiafei, Liu, Zhe
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909613703561216
author Zhang, Chiyu
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Liu, Zhe
author_facet Zhang, Chiyu
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Liu, Zhe
contents With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and generalization; 2) detailed evaluations framework; 3) motivation-driven attack categorizations; and 4) an integrated perspective on both traditional and LVLM attacks. This article addresses these gaps by offering a thorough summary of traditional and LVLM adversarial attacks, emphasizing their connections and distinctions, and providing actionable insights for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
Zhang, Chiyu
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Liu, Zhe
Computer Vision and Pattern Recognition
Cryptography and Security
With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks demystification. However, existing surveys often target attack taxonomy and lack in-depth analysis like 1) unified insights into adversariality, transferability, and generalization; 2) detailed evaluations framework; 3) motivation-driven attack categorizations; and 4) an integrated perspective on both traditional and LVLM attacks. This article addresses these gaps by offering a thorough summary of traditional and LVLM adversarial attacks, emphasizing their connections and distinctions, and providing actionable insights for future research.
title Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2410.23687