X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a critical concern. In this work, we introduce \textbf{X-Transfer}, a novel attack method that exposes a universal adversarial vulnerability in CLIP. X-Transfer generates a Universal Adversarial Perturbation (UAP) capable of deceiving various CLIP encoders and downstream VLMs across different samples, tasks, and domains. We refer to this property as \textbf{super transferability}--a single perturbation achieving cross-data, cross-domain, cross-model, and cross-task adversarial transferability simultaneously. This is achieved through \textbf{surrogate scaling}, a key innovation of our approach. Unlike existing methods that rely on fixed surrogate models, which are computationally intensive to scale, X-Transfer employs an efficient surrogate scaling strategy that dynamically selects a small subset of suitable surrogates from a large search space. Extensive evaluations demonstrate that X-Transfer significantly outperforms previous state-of-the-art UAP methods, establishing a new benchmark for adversarial transferability across CLIP models. The code is publicly available in our \href{https://github.com/HanxunH/XTransferBench}{GitHub repository}.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
Transferable adversarial examples highlight the vulnerability of deep neural networks (DNNs) to imperceptible perturbations across various real-world applications. While there have been notable advancements in untargeted…
A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications
Transfer-based attacks are a practical method of black-box adversarial attacks, in which the attacker aims to craft adversarial examples from a source (surrogate) model that is transferable to the target model. A wide ra…
Towards Transferable Targeted 3D Adversarial Attack in the Physical World
Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the misclassification categories of adversarial samples, posing a greater threat to security-critical tasks. In the m…
Adversarial AttackNeRFTransferable Attack for Semantic Segmentation
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack meth…
Data AugmentationSegmentationSemantic SegmentationDirection-Aggregated Attack for Transferable Adversarial Examples
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model …