Improving the Transferability of Adversarial Examples via Direction Tuning

• URL: http://arxiv.org/abs/2303.15109v2
• Date: Fri, 11 Aug 2023 12:27:42 GMT
• Title: Improving the Transferability of Adversarial Examples via Direction Tuning
• Authors: Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
• Abstract summary: In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. A novel transfer-based attack, namely direction tuning attack, is proposed to decrease the update deviation in the large step length. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples.
• Score: 18.880398046794138
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well. However, directly reducing the update step length will lead to serious update oscillation so that the generated adversarial examples also can not achieve great transferability to the victim models. To address these issues, a novel transfer-based attack, namely direction tuning attack, is proposed to not only decrease the update deviation in the large step length, but also mitigate the update oscillation in the small sampling step length, thereby making the generated adversarial examples converge well to achieve great transferability on victim models. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples. The experiment results on ImageNet demonstrate that the average attack success rate (ASR) of the adversarial examples generated by our method can be improved from 87.9\% to 94.5\% on five victim models without defenses, and from 69.1\% to 76.2\% on eight advanced defense methods, in comparison with that of latest gradient-based attacks.

Related papers

• Generating Adversarial Examples with Better Transferability via Masking Unimportant Parameters of Surrogate Model [6.737574282249396]
  We propose to improve the transferability of adversarial examples in the transfer-based attack via unimportant masking parameters (MUP) The key idea in MUP is to refine the pretrained surrogate models to boost the transfer-based attack.
  arXiv  Detail & Related papers  (2023-04-14T03:06:43Z)
• Fuzziness-tuned: Improving the Transferability of Adversarial Examples [18.880398046794138]
  adversarial examples have been widely used to enhance the robustness of the training models on deep neural networks. The attack success rate of the transfer-based attacks on the surrogate model is much higher than that on victim model under the low attack strength. A fuzziness-tuned method is proposed to ensure the generated adversarial examples can effectively skip out of the fuzzy domain.
  arXiv  Detail & Related papers  (2023-03-17T16:00:18Z)
• Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples [89.85593878754571]
  transferability of adversarial examples across deep neural networks is the crux of many black-box attacks. We advocate to attack a Bayesian model for achieving desirable transferability. Our method outperforms recent state-of-the-arts by large margins.
  arXiv  Detail & Related papers  (2023-02-10T07:08:13Z)
• Improving Adversarial Transferability with Scheduled Step Size and Dual Example [33.00528131208799]
  We show that transferability of adversarial examples generated by the iterative fast gradient sign method exhibits a decreasing trend when increasing the number of iterations. We propose a novel strategy, which uses the Scheduled step size and the Dual example (SD) to fully utilize the adversarial information near the benign sample. Our proposed strategy can be easily integrated with existing adversarial attack methods for better adversarial transferability.
  arXiv  Detail & Related papers  (2023-01-30T15:13:46Z)
• Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning [80.21709045433096]
  A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample. We use metric learning to frame adversarial regularization as an optimal transport problem. Our preliminary results indicate that regularizing over invariant perturbations in our framework improves both invariant and sensitivity defense.
  arXiv  Detail & Related papers  (2022-11-04T13:54:02Z)
• 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)
• 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)
• Direction-Aggregated Attack for Transferable Adversarial Examples [10.208465711975242]
  A deep neural network is vulnerable to adversarial examples crafted by imposing imperceptible changes to the inputs. adversarial examples are most successful in white-box settings where the model and its parameters are available. We propose the Direction-Aggregated adversarial attacks that deliver transferable adversarial examples.
  arXiv  Detail & Related papers  (2021-04-19T09:54:56Z)
• 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)
• 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)
• Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution [83.02632136860976]
  We study black-box adversarial attacks against deep neural networks (DNNs) We develop a novel mechanism of adversarial transferability, which is robust to the surrogate biases. Experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method.
  arXiv  Detail & Related papers  (2020-06-15T16:45:27Z)

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.