paper-with-me

홈 › Papers

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

2025-05-08 · Hanxun Huang, Sarah Erfani, Yige Li, Xingjun Ma, James Bailey

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}.

📄 PDF Abstract BibTeX arXiv:2505.05528

Code (1)

HanxunH/XTransferBench 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks

2025-01-02 · Teng Li, Xingjun Ma, Yu-Gang Jiang

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

2023-09-21 · NeurIPS 2023 11

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

2023-12-15 · CVPR 2024 1 · Yao Huang, Yinpeng Dong, Shouwei Ruan, Xiao Yang 외

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 AttackNeRF

Transferable Attack for Semantic Segmentation

2023-07-31 · Mengqi He, Jing Zhang, Zhaoyuan Yang, Mingyi He 외

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 Segmentation

Direction-Aggregated Attack for Transferable Adversarial Examples

2021-04-19 · Tianjin Huang, Vlado Menkovski, Yulong Pei, Yuhao Wang 외

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 …