Spatial-Frequency Discriminability for Revealing Adversarial Perturbations

• URL: http://arxiv.org/abs/2305.10856v3
• Date: Wed, 7 Aug 2024 04:59:01 GMT
• Title: Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
• Authors: Chao Wang, Shuren Qi, Zhiqiu Huang, Yushu Zhang, Rushi Lan, Xiaochun Cao, Feng-Lei Fan,
• Abstract summary: Vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. Current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. We propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition.
• Score: 53.279716307171604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. However, these decompositions are either biased towards frequency resolution or spatial resolution, thus failing to capture adversarial patterns comprehensively. Also, when the detector relies on few fixed features, it is practical for an adversary to fool the model while evading the detector (i.e., defense-aware attack). Motivated by such facts, we propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition. It expands the above works from two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability, capturing the differences between natural and adversarial data comprehensively in both spatial and frequency distributions, w.r.t. the common trigonometric or wavelet basis; 2) the extensive features formed by the Krawtchouk decomposition allows for adaptive feature selection and secrecy mechanism, significantly increasing the difficulty of the defense-aware attack, w.r.t. the detector with few fixed features. Theoretical and numerical analyses demonstrate the uniqueness and usefulness of our detector, exhibiting competitive scores on several deep models and image sets against a variety of adversarial attacks.

Related papers

• Detecting Adversarial Data via Perturbation Forgery [28.637963515748456]
  adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data. New attacks based on generative models with imbalanced and anisotropic noise patterns evade detection. We propose Perturbation Forgery, which includes noise distribution perturbation, sparse mask generation, and pseudo-adversarial data production, to train an adversarial detector capable of detecting unseen gradient-based, generative-model-based, and physical adversarial attacks.
  arXiv  Detail & Related papers  (2024-05-25T13:34:16Z)
• Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks [62.036798488144306]
  Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. We propose an attack-agnostic defense method named Meta Invariance Defense (MID) We show that MID simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration.
  arXiv  Detail & Related papers  (2024-04-04T10:10:38Z)
• 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)
• A Frequency Perspective of Adversarial Robustness [72.48178241090149]
  We present a frequency-based understanding of adversarial examples, supported by theoretical and empirical findings. Our analysis shows that adversarial examples are neither in high-frequency nor in low-frequency components, but are simply dataset dependent. We propose a frequency-based explanation for the commonly observed accuracy vs. robustness trade-off.
  arXiv  Detail & Related papers  (2021-10-26T19:12:34Z)
• Adversarially Robust One-class Novelty Detection [83.1570537254877]
  We show that existing novelty detectors are susceptible to adversarial examples. We propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.
  arXiv  Detail & Related papers  (2021-08-25T10:41:29Z)
• Demotivate adversarial defense in remote sensing [0.0]
  We study adversarial retraining and adversarial regularization as adversarial defenses to this purpose. We show through several experiments on public remote sensing datasets that adversarial robustness seems uncorrelated to geographic and over-fitting robustness.
  arXiv  Detail & Related papers  (2021-05-28T15:04:37Z)
• From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation [27.04820989579924]
  deep neural networks are not robust against adversarial perturbations. In this work, we study the adversarial problem from a frequency domain perspective. We propose an adversarial defense method based on the well-known Wiener filters.
  arXiv  Detail & Related papers  (2020-12-02T22:06:04Z)
• WaveTransform: Crafting Adversarial Examples via Input Decomposition [69.01794414018603]
  We introduce WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination) Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs.
  arXiv  Detail & Related papers  (2020-10-29T17:16:59Z)
• RAID: Randomized Adversarial-Input Detection for Neural Networks [7.37305608518763]
  We propose a novel technique for adversarial-image detection, RAID, that trains a secondary classifier to identify differences in neuron activation values between benign and adversarial inputs. RAID is more reliable and more effective than the state of the art when evaluated against six popular attacks.
  arXiv  Detail & Related papers  (2020-02-07T13:27:29Z)

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.