Hierarchically Robust Zero-shot Vision-language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Junhao, Zhang, Yifei, Zhu, Hao, Ong, Yew-Soon, Koniusz, Piotr
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910152440938496
author Dong, Junhao
Zhang, Yifei
Zhu, Hao
Ong, Yew-Soon
Koniusz, Piotr
author_facet Dong, Junhao
Zhang, Yifei
Zhu, Hao
Ong, Yew-Soon
Koniusz, Piotr
contents Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding, sacrificing natural performance and robustness. A robustness degradation also occurs when a model faces adversarial attacks targeting superclasses (parent classes, e.g., mammal) in addition to their base (leaf) classes (e.g., cat). Thus, to enhance adversarial robustness and leverage the inherent hierarchical properties of class space, we propose a novel adversarial fine-tuning framework based on hierarchical embeddings and several levels of adversarially robust alignment of image-text modalities. Additional mechanisms place visual embeddings at the desired depth of hierarchy, and we provide a theoretical connection between the depth of embedding in the hierarchy and the maximum viable margin size. Our model naturally realizes several margin sizes, boosting generalization of adversaries for robustification. As various trees with different parent labels can share the same leaf labels, we also consider aligning over multiple trees to boost semantic variety. Experiments across several datasets are performed.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18867
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchically Robust Zero-shot Vision-language Models
Dong, Junhao
Zhang, Yifei
Zhu, Hao
Ong, Yew-Soon
Koniusz, Piotr
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding, sacrificing natural performance and robustness. A robustness degradation also occurs when a model faces adversarial attacks targeting superclasses (parent classes, e.g., mammal) in addition to their base (leaf) classes (e.g., cat). Thus, to enhance adversarial robustness and leverage the inherent hierarchical properties of class space, we propose a novel adversarial fine-tuning framework based on hierarchical embeddings and several levels of adversarially robust alignment of image-text modalities. Additional mechanisms place visual embeddings at the desired depth of hierarchy, and we provide a theoretical connection between the depth of embedding in the hierarchy and the maximum viable margin size. Our model naturally realizes several margin sizes, boosting generalization of adversaries for robustification. As various trees with different parent labels can share the same leaf labels, we also consider aligning over multiple trees to boost semantic variety. Experiments across several datasets are performed.
title Hierarchically Robust Zero-shot Vision-language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.18867