Luring of transferable adversarial perturbations in the black-box paradigm

• URL: http://arxiv.org/abs/2004.04919v3
• Date: Wed, 3 Mar 2021 15:52:41 GMT
• Title: Luring of transferable adversarial perturbations in the black-box paradigm
• Authors: R\'emi Bernhard, Pierre-Alain Moellic, Jean-Max Dutertre
• Abstract summary: We present a new approach to improve the robustness of a model against black-box transfer attacks. A removable additional neural network is included in the target model, and is designed to induce the textitluring effect. Our deception-based method only needs to have access to the predictions of the target model and does not require a labeled data set.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this paper, we pave the way towards a new approach to improve the robustness of a model against black-box transfer attacks. A removable additional neural network is included in the target model, and is designed to induce the \textit{luring effect}, which tricks the adversary into choosing false directions to fool the target model. Training the additional model is achieved thanks to a loss function acting on the logits sequence order. Our deception-based method only needs to have access to the predictions of the target model and does not require a labeled data set. We explain the luring effect thanks to the notion of robust and non-robust useful features and perform experiments on MNIST, SVHN and CIFAR10 to characterize and evaluate this phenomenon. Additionally, we discuss two simple prediction schemes, and verify experimentally that our approach can be used as a defense to efficiently thwart an adversary using state-of-the-art attacks and allowed to perform large perturbations.

Related papers

• OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks [17.584752814352502]
  Evasion Attacks (EA) are used to test the robustness of trained neural networks by distorting input data. We introduce a self-supervised, computationally economical method for generating adversarial examples. Our experiments consistently demonstrate the method is effective across various models, unseen data categories, and even defended models.
  arXiv  Detail & Related papers  (2023-10-05T17:34:47Z)
• Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks [23.010308600769545]
  Deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. We propose a simple and lightweight defense against black-box attacks by adding random noise to hidden features at intermediate layers of the model at inference time. Our method effectively enhances the model's resilience against both score-based and decision-based black-box attacks.
  arXiv  Detail & Related papers  (2023-10-01T03:53:23Z)
• 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)
• Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries [69.53730499849023]
  We show that adversarial examples can be successfully transferred to another independently trained model to induce prediction errors. We propose a deep learning-based pre-processing mechanism, which we refer to as a robust transferable feature extractor (RTFE)
  arXiv  Detail & Related papers  (2022-09-14T21:09:34Z)
• What Does the Gradient Tell When Attacking the Graph Structure [44.44204591087092]
  We present a theoretical demonstration revealing that attackers tend to increase inter-class edges due to the message passing mechanism of GNNs. By connecting dissimilar nodes, attackers can more effectively corrupt node features, making such attacks more advantageous. We propose an innovative attack loss that balances attack effectiveness and imperceptibility, sacrificing some attack effectiveness to attain greater imperceptibility.
  arXiv  Detail & Related papers  (2022-08-26T15:45:20Z)
• Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations [54.1807206010136]
  Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. We propose Adversarial Pixel Restoration as a self-supervised alternative to train an effective surrogate model from scratch. Our training approach is based on a min-max objective which reduces overfitting via an adversarial objective.
  arXiv  Detail & Related papers  (2022-07-18T17:59:58Z)
• Combating Adversaries with Anti-Adversaries [118.70141983415445]
  In particular, our layer generates an input perturbation in the opposite direction of the adversarial one. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models. Our anti-adversary layer significantly enhances model robustness while coming at no cost on clean accuracy.
  arXiv  Detail & Related papers  (2021-03-26T09:36:59Z)
• 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)
• Query-Free Adversarial Transfer via Undertrained Surrogates [14.112444998191698]
  We introduce a new method for improving the efficacy of adversarial attacks in a black-box setting by undertraining the surrogate model which the attacks are generated on. We show that this method transfers well across architectures and outperforms state-of-the-art methods by a wide margin.
  arXiv  Detail & Related papers  (2020-07-01T23:12:22Z)
• 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)
• GAP++: Learning to generate target-conditioned adversarial examples [28.894143619182426]
  Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. We propose a more general-purpose framework which infers target-conditioned perturbations dependent on both input image and target label. Our method achieves superior performance with single target attack models and obtains high fooling rates with small perturbation norms.
  arXiv  Detail & Related papers  (2020-06-09T07:49:49Z)

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.