paper-with-me

홈 › Papers

An h-space Based Adversarial Attack for Protection Against Few-shot Personalization

2025-07-23 · Xide Xu, Sandesh Kamath, Muhammad Atif Butt, Bogdan Raducanu arxiv

The versatility of diffusion models in generating customized images from few samples raises significant privacy concerns, particularly regarding unauthorized modifications of private content. This concerning issue has renewed the efforts in developing protection mechanisms based on adversarial attacks, which generate effective perturbations to poison diffusion models. Our work is motivated by the observation that these models exhibit a high degree of abstraction within their semantic latent space (`h-space'), which encodes critical high-level features for generating coherent and meaningful content. In this paper, we propose a novel anti-customization approach, called HAAD (h-space based Adversarial Attack for Diffusion models), that leverages adversarial attacks to craft perturbations based on the h-space that can efficiently degrade the image generation process. Building upon HAAD, we further introduce a more efficient variant, HAAD-KV, that constructs perturbations solely based on the KV parameters of the h-space. This strategy offers a stronger protection, that is computationally less expensive. Despite their simplicity, our methods outperform state-of-the-art adversarial attacks, highlighting their effectiveness.

📄 PDF Abstract BibTeX arXiv:2507.17554

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackImage Generation

Similar Papers 제목 키워드 기반

Defending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems

2025-01-23 · Ping He, Lorenzo Cavallaro, Shouling Ji

Android malware presents a persistent threat to users' privacy and data integrity. To combat this, researchers have proposed machine learning-based (ML-based) Android malware detection (AMD) systems. However, adversarial…

Adversarial RobustnessAndroid Malware DetectionMalware Detection

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think

2024-04-20 · Haotian Xue, Yongxin Chen

Adversarial examples for diffusion models are widely used as solutions for safety concerns. By adding adversarial perturbations to personal images, attackers can not edit or imitate them easily. However, it is essential …

Robust Neural Networks using Randomized Adversarial Training

2019-03-25 · Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Negrevergne

This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that def…

Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems

2025-08-03 · Zhongliang Guo, Yifei Qian, Yanli Li, Weiye Li 외 arxiv

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines th…

Computational EfficiencyAdversarial AttackStyle Transfer

Towards Defending against Adversarial Examples via Attack-Invariant Features

2021-06-09 · Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang 외

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen t…

Adversarial Robustness