Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers

• URL: http://arxiv.org/abs/2408.01705v1
• Date: Sat, 3 Aug 2024 08:07:03 GMT
• Title: Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
• Authors: Weijie Zheng, Xingjun Ma, Hanxun Huang, Zuxuan Wu, Yu-Gang Jiang,
• Abstract summary: This paper studies the transferability of such an adversarial vulnerability from a pre-trained ViT model to downstream tasks. We show that DTA achieves an average attack success rate (ASR) exceeding 90%, surpassing existing methods by a huge margin.
• Score: 95.22517830759193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications. However, studies have shown that, like convolutional neural networks (CNNs), ViTs are also susceptible to adversarial attacks, where subtle perturbations in the input can fool the model into making false predictions. This paper studies the transferability of such an adversarial vulnerability from a pre-trained ViT model to downstream tasks. We focus on \emph{sample-wise} transfer attacks and propose a novel attack method termed \emph{Downstream Transfer Attack (DTA)}. For a given test image, DTA leverages a pre-trained ViT model to craft the adversarial example and then applies the adversarial example to attack a fine-tuned version of the model on a downstream dataset. During the attack, DTA identifies and exploits the most vulnerable layers of the pre-trained model guided by a cosine similarity loss to craft highly transferable attacks. Through extensive experiments with pre-trained ViTs by 3 distinct pre-training methods, 3 fine-tuning schemes, and across 10 diverse downstream datasets, we show that DTA achieves an average attack success rate (ASR) exceeding 90\%, surpassing existing methods by a huge margin. When used with adversarial training, the adversarial examples generated by our DTA can significantly improve the model's robustness to different downstream transfer attacks.

Related papers

• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability [24.272384832200522]
  We propose a novel approach that directly constructs adversarial examples by extracting transferable features across various tasks. Specifically, we train a sequence-to-sequence generative model named CT-GAT using adversarial sample data collected from multiple tasks to acquire universal adversarial features. Results demonstrate that our method achieves superior attack performance with small cost.
  arXiv  Detail & Related papers  (2023-10-22T11:00:04Z)
• Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability [17.899587145780817]
  Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. We propose the DUMB attacker model, which allows analyzing if evasion attacks fail to transfer when the training conditions of surrogate and victim models differ. Our analysis, which generated 13K tests over 14 distinct attacks, led to numerous novel findings in the scope of transferable attacks with surrogate models.
  arXiv  Detail & Related papers  (2023-06-27T10:21:27Z)
• Can Adversarial Examples Be Parsed to Reveal Victim Model Information? [62.814751479749695]
  In this work, we ask whether it is possible to infer data-agnostic victim model (VM) information from data-specific adversarial instances. We collect a dataset of adversarial attacks across 7 attack types generated from 135 victim models. We show that a simple, supervised model parsing network (MPN) is able to infer VM attributes from unseen adversarial attacks.
  arXiv  Detail & Related papers  (2023-03-13T21:21:49Z)
• Learning to Learn Transferable Attack [77.67399621530052]
  Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. We propose a Learning to Learn Transferable Attack (LLTA) method, which makes the adversarial perturbations more generalized via learning from both data and model augmentation. Empirical results on the widely-used dataset demonstrate the effectiveness of our attack method with a 12.85% higher success rate of transfer attack compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-10T07:24:21Z)
• Towards Transferable Adversarial Attacks on Vision Transformers [110.55845478440807]
  Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. We introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs.
  arXiv  Detail & Related papers  (2021-09-09T11:28:25Z)
• Practical No-box Adversarial Attacks against DNNs [31.808770437120536]
  We investigate no-box adversarial examples, where the attacker can neither access the model information or the training set nor query the model. We propose three mechanisms for training with a very small dataset and find that prototypical reconstruction is the most effective. Our approach significantly diminishes the average prediction accuracy of the system to only 15.40%, which is on par with the attack that transfers adversarial examples from a pre-trained Arcface model.
  arXiv  Detail & Related papers  (2020-12-04T11:10:03Z)
• Defense-guided Transferable Adversarial Attacks [5.2206166148727835]
  adversarial examples are hard to transfer to unknown models. We design a max-min framework inspired by input transformations, which are benificial to both the adversarial attack and defense. Our method is expected to be a benchmark for assessing the robustness of deep models.
  arXiv  Detail & Related papers  (2020-10-22T08:51:45Z)
• DaST: Data-free Substitute Training for Adversarial Attacks [55.76371274622313]
  We propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks. To achieve this, DaST utilizes specially designed generative adversarial networks (GANs) to train the substitute models. Experiments demonstrate the substitute models can achieve competitive performance compared with the baseline models.
  arXiv  Detail & Related papers  (2020-03-28T04:28:13Z)

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.