Robust image classification with multi-modal large language models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Villani, Francesco, Maljkovic, Igor, Lazzaro, Dario, Sotgiu, Angelo, Cinà, Antonio Emanuele, Roli, Fabio
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915249467162624
author Villani, Francesco
Maljkovic, Igor
Lazzaro, Dario
Sotgiu, Angelo
Cinà, Antonio Emanuele
Roli, Fabio
author_facet Villani, Francesco
Maljkovic, Igor
Lazzaro, Dario
Sotgiu, Angelo
Cinà, Antonio Emanuele
Roli, Fabio
contents Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and detection-based defenses have been proposed to strengthen models in advance. However, most of these approaches focus on a single data modality, overlooking the relationships between visual patterns and textual descriptions of the input. In this paper, we propose a novel defense, MultiShield, designed to combine and complement these defenses with multi-modal information to further enhance their robustness. MultiShield leverages multi-modal large language models to detect adversarial examples and abstain from uncertain classifications when there is no alignment between textual and visual representations of the input. Extensive evaluations on CIFAR-10 and ImageNet datasets, using robust and non-robust image classification models, demonstrate that MultiShield can be easily integrated to detect and reject adversarial examples, outperforming the original defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust image classification with multi-modal large language models
Villani, Francesco
Maljkovic, Igor
Lazzaro, Dario
Sotgiu, Angelo
Cinà, Antonio Emanuele
Roli, Fabio
Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and detection-based defenses have been proposed to strengthen models in advance. However, most of these approaches focus on a single data modality, overlooking the relationships between visual patterns and textual descriptions of the input. In this paper, we propose a novel defense, MultiShield, designed to combine and complement these defenses with multi-modal information to further enhance their robustness. MultiShield leverages multi-modal large language models to detect adversarial examples and abstain from uncertain classifications when there is no alignment between textual and visual representations of the input. Extensive evaluations on CIFAR-10 and ImageNet datasets, using robust and non-robust image classification models, demonstrate that MultiShield can be easily integrated to detect and reject adversarial examples, outperforming the original defenses.
title Robust image classification with multi-modal large language models
topic Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2412.10353