Scaling Laws for Black box Adversarial Attacks

• URL: http://arxiv.org/abs/2411.16782v3
• Date: Sun, 29 Jun 2025 16:32:50 GMT
• Title: Scaling Laws for Black box Adversarial Attacks
• Authors: Chuan Liu, Huanran Chen, Yichi Zhang, Yinpeng Dong, Jun Zhu,
• Abstract summary: Adversarial examples usually exhibit good cross-model transferability.<n>Model ensembling is an effective strategy to improve the transferability of adversarial examples.<n>By scaling law, we achieve 90%+ transfer attack success rate on even proprietary models.
• Score: 37.744814957775965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial examples usually exhibit good cross-model transferability, enabling attacks on black-box models with limited information about their architectures and parameters, which are highly threatening in commercial black-box scenarios. Model ensembling is an effective strategy to improve the transferability of adversarial examples by attacking multiple surrogate models. However, since prior studies usually adopt few models in the ensemble, there remains an open question of whether scaling the number of models can further improve black-box attacks. Inspired by the scaling law of large foundation models, we investigate the scaling laws of black-box adversarial attacks in this work. Through theoretical analysis and empirical evaluations, we conclude with clear scaling laws that using more surrogate models enhances adversarial transferability. Comprehensive experiments verify the claims on standard image classifiers, diverse defended models and multimodal large language models using various adversarial attack methods. Specifically, by scaling law, we achieve 90%+ transfer attack success rate on even proprietary models like GPT-4o. Further visualization indicates that there is also a scaling law on the interpretability and semantics of adversarial perturbations.

Related papers

• An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability [26.39964737311377]
  We propose an adaptive ensemble attack, dubbed AdaEA, to adaptively control the fusion of the outputs from each model. We achieve considerable improvement over the existing ensemble attacks on various datasets.
  arXiv  Detail & Related papers  (2023-08-05T15:12:36Z)
• Rethinking Model Ensemble in Transfer-based Adversarial Attacks [46.82830479910875]
  An effective strategy to improve the transferability is attacking an ensemble of models. Previous works simply average the outputs of different models. We propose a Common Weakness Attack (CWA) to generate more transferable adversarial examples.
  arXiv  Detail & Related papers  (2023-03-16T06:37:16Z)
• Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks [30.863450425927613]
  We study the black-box targeted attack problem from the model discrepancy perspective. We present a generalization error bound for black-box targeted attacks, which gives a rigorous theoretical analysis for guaranteeing the success of the attack. We derive a new algorithm for black-box targeted attacks based on our theoretical analysis.
  arXiv  Detail & Related papers  (2022-12-18T08:19:08Z)
• Frequency Domain Model Augmentation for Adversarial Attack [91.36850162147678]
  For black-box attacks, the gap between the substitute model and the victim model is usually large. We propose a novel spectrum simulation attack to craft more transferable adversarial examples against both normally trained and defense models.
  arXiv  Detail & Related papers  (2022-07-12T08:26:21Z)
• Harnessing Perceptual Adversarial Patches for Crowd Counting [92.79051296850405]
  Crowd counting is vulnerable to adversarial examples in the physical world. This paper proposes the Perceptual Adrial Patch (PAP) generation framework to learn the shared perceptual features between models.
  arXiv  Detail & Related papers  (2021-09-16T13:51:39Z)
• Training Meta-Surrogate Model for Transferable Adversarial Attack [98.13178217557193]
  We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. We show we can obtain a Meta-Surrogate Model (MSM) such that attacks to this model can be easier transferred to other models.
  arXiv  Detail & Related papers  (2021-09-05T03:27:46Z)
• Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning [60.784641458579124]
  We show that fine-tuning effectively enhances model robustness under white-box FGSM attacks. We also propose a black-box attack method for transfer learning models which attacks the target model with the adversarial examples produced by its source model. To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
  arXiv  Detail & Related papers  (2020-08-25T15:04:32Z)
• Orthogonal Deep Models As Defense Against Black-Box Attacks [71.23669614195195]
  We study the inherent weakness of deep models in black-box settings where the attacker may develop the attack using a model similar to the targeted model. We introduce a novel gradient regularization scheme that encourages the internal representation of a deep model to be orthogonal to another. We verify the effectiveness of our technique on a variety of large-scale models.
  arXiv  Detail & Related papers  (2020-06-26T08:29:05Z)

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.