LGAICRJul 13, 2023

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks

arXiv:2307.06608v31 citationsh-index: 32
Originality Highly original
AI Analysis

This addresses the vulnerability of deep neural networks in safety-critical applications by improving no-box attacks, which are practical but underexplored, representing a strong specific gain in the domain of adversarial machine learning.

The paper tackles the problem of no-box adversarial attacks, where attackers lack prior knowledge of the target model, by proposing MF-CLIP, a framework that enhances CLIP's effectiveness as a surrogate model through margin-aware feature space optimization, resulting in a 15.23% improvement over baselines on standard models and a 9.52% improvement on adversarially trained models.

The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research has addressed various attack scenarios, the no-box attack setting where adversaries have no prior knowledge, including access to training data of the target model, remains relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs), particularly CLIP, as surrogate models for executing no-box attacks. Our theoretical and empirical analyses reveal a key limitation in the execution of no-box attacks stemming from insufficient discriminative capabilities for direct application of vanilla CLIP as a surrogate model. To address this limitation, we propose MF-CLIP: a novel framework that enhances CLIP's effectiveness as a surrogate model through margin-aware feature space optimization. Comprehensive evaluations across diverse architectures and datasets demonstrate that MF-CLIP substantially advances the state-of-the-art in no-box attacks, surpassing existing baselines by 15.23% on standard models and achieving a 9.52% improvement on adversarially trained models. Our code will be made publicly available to facilitate reproducibility and future research in this direction.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes