Robust Classification with Multi-Modal Models

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, Multi-Shield, designed to combine and complement these defenses with multimodal information to further enhance their robustness. Multi-Shield leverages multimodal 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 six distinct datasets, using robust and non-robust image classification models, demonstrate that Multi-Shield can be easily integrated to detect and reject adversarial examples, outperforming the original defenses.