Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations

• URL: http://arxiv.org/abs/2009.13714v4
• Date: Wed, 17 Aug 2022 23:00:11 GMT
• Title: Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations
• Authors: Pu Zhao, Parikshit Ram, Songtao Lu, Yuguang Yao, Djallel Bouneffouf, Xue Lin, Sijia Liu
• Abstract summary: A universal adversarial perturbation (UAP) can simultaneously attack multiple images. The existing UAP generator is underdeveloped when images are drawn from different image sources. We take a novel view of UAP generation as a customized instance of few-shot learning.
• Score: 65.66102345372758
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Adversarial perturbations are critical for certifying the robustness of deep learning models. A universal adversarial perturbation (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an image-wise attack algorithm. However, the existing UAP generator is underdeveloped when images are drawn from different image sources (e.g., with different image resolutions). Towards an authentic universality across image sources, we take a novel view of UAP generation as a customized instance of few-shot learning, which leverages bilevel optimization and learning-to-optimize (L2O) techniques for UAP generation with improved attack success rate (ASR). We begin by considering the popular model agnostic meta-learning (MAML) framework to meta-learn a UAP generator. However, we see that the MAML framework does not directly offer the universal attack across image sources, requiring us to integrate it with another meta-learning framework of L2O. The resulting scheme for meta-learning a UAP generator (i) has better performance (50% higher ASR) than baselines such as Projected Gradient Descent, (ii) has better performance (37% faster) than the vanilla L2O and MAML frameworks (when applicable), and (iii) is able to simultaneously handle UAP generation for different victim models and image data sources.

Related papers

• Towards Generative Class Prompt Learning for Fine-grained Visual Recognition [5.633314115420456]
  Generative Class Prompt Learning and Contrastive Multi-class Prompt Learning are presented. Generative Class Prompt Learning improves visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation.
  arXiv  Detail & Related papers  (2024-09-03T12:34:21Z)
• Texture Re-scalable Universal Adversarial Perturbation [61.33178492209849]
  We propose texture scale-constrained UAP, which automatically generates UAPs with category-specific local textures. TSC-UAP achieves a considerable improvement in the fooling ratio and attack transferability for both data-dependent and data-free UAP methods.
  arXiv  Detail & Related papers  (2024-06-10T08:18:55Z)
• Mixture of Low-rank Experts for Transferable AI-Generated Image Detection [18.631006488565664]
  Generative models have shown a giant leap in photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector capable of identifying images from diverse sources. Inspired by the zero-shot transferability of pre-trained vision-language models, we seek to harness the non-trivial visual-world knowledge and descriptive proficiency of CLIP-ViT to generalize over unknown domains.
  arXiv  Detail & Related papers  (2024-04-07T09:01:50Z)
• Raising the Bar of AI-generated Image Detection with CLIP [50.345365081177555]
  The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios.
  arXiv  Detail & Related papers  (2023-11-30T21:11:20Z)
• SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation [61.732503554088524]
  We investigate whether it is possible to attack Segment Anything Model (SAM) with image-aversagnostic Universal Adrial Perturbation (UAP) We propose a novel perturbation-centric framework that results in a UAP generation method based on self-supervised contrastive learning (CL) The effectiveness of our proposed CL-based UAP generation method is validated by both quantitative and qualitative results.
  arXiv  Detail & Related papers  (2023-10-19T02:49:24Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• The race to robustness: exploiting fragile models for urban camouflage and the imperative for machine learning security [0.0]
  This paper presents Distributed Adversarial Regions (DAR), a novel method that implements distributed instantiations of computer vision-based AML attack methods. We consider the context of object detection models used in urban environments, and benchmark the MobileNetV2, NasNetMobile and DenseNet169 models. We find that DARs can cause a reduction in confidence of 40.4% on average, but with the benefit of not requiring the entire image.
  arXiv  Detail & Related papers  (2023-06-26T11:32:40Z)
• Transferable Universal Adversarial Perturbations Using Generative Models [29.52528162520099]
  Image-agnostic perturbations (UAPs) can fool deep neural networks with high confidence. We propose a novel technique for generating more transferable UAPs. We obtain an average fooling rate of 93.36% on the source models.
  arXiv  Detail & Related papers  (2020-10-28T12:31:59Z)
• Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks [154.31827097264264]
  Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. We propose Dual Manifold Adversarial Training (DMAT) where adversarial perturbations in both latent and image spaces are used in robustifying the model. Our DMAT improves performance on normal images, and achieves comparable robustness to the standard adversarial training against Lp attacks.
  arXiv  Detail & Related papers  (2020-09-05T06:00:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.