Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ghiasvand, Sajjad, Oskouie, Haniyeh Ehsani, Alizadeh, Mahnoosh, Pedarsani, Ramtin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916971054891008
author Ghiasvand, Sajjad
Oskouie, Haniyeh Ehsani
Alizadeh, Mahnoosh
Pedarsani, Ramtin
author_facet Ghiasvand, Sajjad
Oskouie, Haniyeh Ehsani
Alizadeh, Mahnoosh
Pedarsani, Ramtin
contents Vision-Language Models (VLMs) such as CLIP have shown remarkable performance in cross-modal tasks through large-scale contrastive pre-training. To adapt these large transformer-based models efficiently for downstream tasks, Parameter-Efficient Fine-Tuning (PEFT) techniques like (Low-Rank Adaptation) LoRA have emerged as scalable alternatives to full fine-tuning, especially in few-shot scenarios. However, like traditional deep neural networks, VLMs are highly vulnerable to adversarial attacks, where imperceptible perturbations can significantly degrade model performance. Adversarial training remains the most effective strategy for improving model robustness in PEFT. In this work, we propose AdvCLIP-LoRA, to our knowledge the first method designed to enhance the adversarial robustness of CLIP models fine-tuned with LoRA in few-shot settings. Our method formulates training as a minimax optimization over low-rank adapters and adversarial perturbations, enabling robust adaptation with a small trainable footprint. Across eight datasets and two backbones (ViT-B/16 and ViT-B/32), AdvCLIP-LoRA achieves state-of-the-art performance in few-shot classification, adversarial base-to-new generalization, and cross-dataset transfer, delivering higher adversarial robustness than prompt tuning baselines without sacrificing much clean accuracy. These findings highlight AdvCLIP-LoRA as a practical approach for robust adaptation of VLMs in resource-constrained settings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15130
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models
Ghiasvand, Sajjad
Oskouie, Haniyeh Ehsani
Alizadeh, Mahnoosh
Pedarsani, Ramtin
Machine Learning
Vision-Language Models (VLMs) such as CLIP have shown remarkable performance in cross-modal tasks through large-scale contrastive pre-training. To adapt these large transformer-based models efficiently for downstream tasks, Parameter-Efficient Fine-Tuning (PEFT) techniques like (Low-Rank Adaptation) LoRA have emerged as scalable alternatives to full fine-tuning, especially in few-shot scenarios. However, like traditional deep neural networks, VLMs are highly vulnerable to adversarial attacks, where imperceptible perturbations can significantly degrade model performance. Adversarial training remains the most effective strategy for improving model robustness in PEFT. In this work, we propose AdvCLIP-LoRA, to our knowledge the first method designed to enhance the adversarial robustness of CLIP models fine-tuned with LoRA in few-shot settings. Our method formulates training as a minimax optimization over low-rank adapters and adversarial perturbations, enabling robust adaptation with a small trainable footprint. Across eight datasets and two backbones (ViT-B/16 and ViT-B/32), AdvCLIP-LoRA achieves state-of-the-art performance in few-shot classification, adversarial base-to-new generalization, and cross-dataset transfer, delivering higher adversarial robustness than prompt tuning baselines without sacrificing much clean accuracy. These findings highlight AdvCLIP-LoRA as a practical approach for robust adaptation of VLMs in resource-constrained settings.
title Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models
topic Machine Learning
url https://arxiv.org/abs/2505.15130