Robust image classification with multi-modal large language models
This addresses the problem of adversarial robustness in image classification for AI security, but it is incremental as it builds on existing defenses by adding multi-modal information.
The paper tackles the vulnerability of deep neural networks to adversarial examples by proposing MultiShield, a defense that uses multi-modal large language models to detect and reject such examples, outperforming original defenses on CIFAR-10 and ImageNet datasets.
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.