Improving the Transferability of Adversarial Examples with the Adam Optimizer

• URL: http://arxiv.org/abs/2012.00567v1
• Date: Tue, 1 Dec 2020 15:18:19 GMT
• Title: Improving the Transferability of Adversarial Examples with the Adam Optimizer
• Authors: Heng Yin, Hengwei Zhang, Jindong Wang and Ruiyu Dou
• Abstract summary: This study combines an improved Adam gradient descent algorithm with the iterative gradient-based attack method. Experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. Our best black-box attack achieved a success rate of 81.9% on a normally trained network and 38.7% on an adversarially trained network.
• Score: 11.210560572849383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are produced by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems. Sophisticated adversarial examples with strong attack performance can also be used as a tool to evaluate the robustness of a model. However, the success rate of adversarial attacks remains to be further improved in black-box environments. Therefore, this study combines an improved Adam gradient descent algorithm with the iterative gradient-based attack method. The resulting Adam Iterative Fast Gradient Method is then used to improve the transferability of adversarial examples. Extensive experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. Our best black-box attack achieved a success rate of 81.9% on a normally trained network and 38.7% on an adversarially trained network.

Related papers

• Enhancing Adversarial Attacks: The Similar Target Method [6.293148047652131]
  adversarial examples pose a threat to deep neural networks' applications. Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. We propose a similar targeted attack method named Similar Target(ST)
  arXiv  Detail & Related papers  (2023-08-21T14:16:36Z)
• Adaptive Perturbation for Adversarial Attack [50.77612889697216]
  We propose a new gradient-based attack method for adversarial examples. We use the exact gradient direction with a scaling factor for generating adversarial perturbations. Our method exhibits higher transferability and outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-27T07:57:41Z)
• Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness [53.094682754683255]
  We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically. Our method learns the in adversarial attacks parameterized by a recurrent neural network. We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
  arXiv  Detail & Related papers  (2021-10-13T13:54:24Z)
• Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks [56.96241557830253]
  Transfer-based adversarial attacks can effectively evaluate model robustness in the black-box setting. We propose a conditional generative attacking model, which can generate the adversarial examples targeted at different classes. Our method improves the success rates of targeted black-box attacks by a significant margin over the existing methods.
  arXiv  Detail & Related papers  (2021-07-05T06:17:47Z)
• Improving Adversarial Transferability with Gradient Refining [7.045900712659982]
  Adversarial examples are crafted by adding human-imperceptible perturbations to original images. Deep neural networks are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to original images.
  arXiv  Detail & Related papers  (2021-05-11T07:44:29Z)
• Boosting Adversarial Transferability through Enhanced Momentum [50.248076722464184]
  Deep learning models are vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Various momentum iterative gradient-based methods are shown to be effective to improve the adversarial transferability. We propose an enhanced momentum iterative gradient-based method to further enhance the adversarial transferability.
  arXiv  Detail & Related papers  (2021-03-19T03:10:32Z)
• Adversarial example generation with AdaBelief Optimizer and Crop Invariance [8.404340557720436]
  Adversarial attacks can be an important method to evaluate and select robust models in safety-critical applications. We propose AdaBelief Iterative Fast Gradient Method (ABI-FGM) and Crop-Invariant attack Method (CIM) to improve the transferability of adversarial examples. Our method has higher success rates than state-of-the-art gradient-based attack methods.
  arXiv  Detail & Related papers  (2021-02-07T06:00:36Z)
• Random Transformation of Image Brightness for Adversarial Attack [5.405413975396116]
  adversarial examples are crafted by adding small, human-imperceptibles to the original images. Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptibles to the original images. We propose an adversarial example generation method based on this phenomenon, which can be integrated with Fast Gradient Sign Method. Our method has a higher success rate for black-box attacks than other attack methods based on data augmentation.
  arXiv  Detail & Related papers  (2021-01-12T07:00:04Z)
• Making Adversarial Examples More Transferable and Indistinguishable [7.885043234081768]
  We propose a method to generate indistinguishable adversarial examples with high transferability. Our best transfer-based attack NI-TI-DI-AITM can fool six classic defense models with an average success rate of 89.3%.
  arXiv  Detail & Related papers  (2020-07-08T01:12:56Z)
• Towards Transferable Adversarial Attack against Deep Face Recognition [58.07786010689529]
  Deep convolutional neural networks (DCNNs) have been found to be vulnerable to adversarial examples. transferable adversarial examples can severely hinder the robustness of DCNNs. We propose DFANet, a dropout-based method used in convolutional layers, which can increase the diversity of surrogate models. We generate a new set of adversarial face pairs that can successfully attack four commercial APIs without any queries.
  arXiv  Detail & Related papers  (2020-04-13T06:44:33Z)
• Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [51.31334977346847]
  We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
  arXiv  Detail & Related papers  (2020-04-01T09:31:10Z)

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.