On The Relationship Between Universal Adversarial Attacks And Sparse Representations

• URL: http://arxiv.org/abs/2311.08265v1
• Date: Tue, 14 Nov 2023 16:00:29 GMT
• Title: On The Relationship Between Universal Adversarial Attacks And Sparse Representations
• Authors: Dana Weitzner and Raja Giryes
• Abstract summary: We show the connection between adversarial attacks and sparse representations. Common attacks on neural networks can be expressed as attacks on the sparse representation of the input image.
• Score: 38.43938212884298
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this vulnerability through the framework of sparsity. We show the connection between adversarial attacks and sparse representations, with a focus on explaining the universality and transferability of adversarial examples in neural networks. To this end, we show that sparse coding algorithms, and the neural network-based learned iterative shrinkage thresholding algorithm (LISTA) among them, suffer from this sensitivity, and that common attacks on neural networks can be expressed as attacks on the sparse representation of the input image. The phenomenon that we observe holds true also when the network is agnostic to the sparse representation and dictionary, and thus can provide a possible explanation for the universality and transferability of adversarial attacks. The code is available at https://github.com/danawr/adversarial_attacks_and_sparse_representations.

Related papers

• Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks [54.565579874913816]
  Neural networks demonstrate inherent vulnerability to small, non-random perturbations, emerging as adversarial attacks. A mathematical congruence manifests between this mechanism and the quantum physics' uncertainty principle, casting light on a hitherto unanticipated interdisciplinarity.
  arXiv  Detail & Related papers  (2024-02-16T02:11:27Z)
• Investigating Human-Identifiable Features Hidden in Adversarial Perturbations [54.39726653562144]
  Our study explores up to five attack algorithms across three datasets. We identify human-identifiable features in adversarial perturbations. Using pixel-level annotations, we extract such features and demonstrate their ability to compromise target models.
  arXiv  Detail & Related papers  (2023-09-28T22:31:29Z)
• SAIF: Sparse Adversarial and Imperceptible Attack Framework [7.025774823899217]
  We propose a novel attack technique called Sparse Adversarial and Interpretable Attack Framework (SAIF) Specifically, we design imperceptible attacks that contain low-magnitude perturbations at a small number of pixels and leverage these sparse attacks to reveal the vulnerability of classifiers. SAIF computes highly imperceptible and interpretable adversarial examples, and outperforms state-of-the-art sparse attack methods on the ImageNet dataset.
  arXiv  Detail & Related papers  (2022-12-14T20:28:50Z)
• Searching for the Essence of Adversarial Perturbations [73.96215665913797]
  We show that adversarial perturbations contain human-recognizable information, which is the key conspirator responsible for a neural network's erroneous prediction. This concept of human-recognizable information allows us to explain key features related to adversarial perturbations.
  arXiv  Detail & Related papers  (2022-05-30T18:04:57Z)
• Adversarial Attacks on Spiking Convolutional Networks for Event-based Vision [0.6999740786886537]
  We show how white-box adversarial attack algorithms can be adapted to the discrete and sparse nature of event-based visual data. We also verify, for the first time, the effectiveness of these perturbations directly on neuromorphic hardware.
  arXiv  Detail & Related papers  (2021-10-06T17:20:05Z)
• Controlled Caption Generation for Images Through Adversarial Attacks [85.66266989600572]
  We study adversarial examples for vision and language models, which typically adopt a Convolutional Neural Network (i.e., CNN) for image feature extraction and a Recurrent Neural Network (RNN) for caption generation. In particular, we investigate attacks on the visual encoder's hidden layer that is fed to the subsequent recurrent network. We propose a GAN-based algorithm for crafting adversarial examples for neural image captioning that mimics the internal representation of the CNN.
  arXiv  Detail & Related papers  (2021-07-07T07:22:41Z)
• Attack to Fool and Explain Deep Networks [59.97135687719244]
  We counter-argue by providing evidence of human-meaningful patterns in adversarial perturbations. Our major contribution is a novel pragmatic adversarial attack that is subsequently transformed into a tool to interpret the visual models.
  arXiv  Detail & Related papers  (2021-06-20T03:07:36Z)
• Exploring Adversarial Examples via Invertible Neural Networks [10.320129984220857]
  Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can introduce real-world threats into systems that rely on neural networks. We propose a new way of achieving such understanding through a recent development, namely, invertible neural models with Lipschitz continuous mapping functions from the input to the output.
  arXiv  Detail & Related papers  (2020-12-24T05:17:21Z)
• Relationship between manifold smoothness and adversarial vulnerability in deep learning with local errors [2.7834038784275403]
  We study the origin of the adversarial vulnerability in artificial neural networks. Our study reveals that a high generalization accuracy requires a relatively fast power-law decay of the eigen-spectrum of hidden representations.
  arXiv  Detail & Related papers  (2020-07-04T08:47:51Z)

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.