Explainable Adversarial Attacks on Coarse-to-Fine Classifiers
- URL: http://arxiv.org/abs/2501.10906v1
- Date: Sun, 19 Jan 2025 00:23:02 GMT
- Title: Explainable Adversarial Attacks on Coarse-to-Fine Classifiers
- Authors: Akram Heidarizadeh, Connor Hatfield, Lorenzo Lazzarotto, HanQin Cai, George Atia,
- Abstract summary: In this paper, we introduce instance-based adversarial attacks for multi-stage classifiers.
Our approach generates explainable adversarial perturbations by utilizing LRP to identify and target key features critical for both coarse and fine-grained classifications.
Unlike conventional attacks, our method not only induces misclassification but also enhances the interpretability of the model's behavior across classification stages.
- Score: 4.1608968552041565
- License:
- Abstract: Traditional adversarial attacks typically aim to alter the predicted labels of input images by generating perturbations that are imperceptible to the human eye. However, these approaches often lack explainability. Moreover, most existing work on adversarial attacks focuses on single-stage classifiers, but multi-stage classifiers are largely unexplored. In this paper, we introduce instance-based adversarial attacks for multi-stage classifiers, leveraging Layer-wise Relevance Propagation (LRP), which assigns relevance scores to pixels based on their influence on classification outcomes. Our approach generates explainable adversarial perturbations by utilizing LRP to identify and target key features critical for both coarse and fine-grained classifications. Unlike conventional attacks, our method not only induces misclassification but also enhances the interpretability of the model's behavior across classification stages, as demonstrated by experimental results.
Related papers
- Adversarial Counterfactual Visual Explanations [0.7366405857677227]
This paper proposes an elegant method to turn adversarial attacks into semantically meaningful perturbations.
The proposed approach hypothesizes that Denoising Diffusion Probabilistic Models are excellent regularizers for avoiding high-frequency and out-of-distribution perturbations.
arXiv Detail & Related papers (2023-03-17T13:34:38Z) - Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity [22.28011382580367]
adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations.
We propose a novel algorithm that attacks semantic similarity on feature representations.
For imperceptibility, we introduce the low-frequency constraint to limit perturbations within high-frequency components.
arXiv Detail & Related papers (2022-03-10T04:46:51Z) - Towards A Conceptually Simple Defensive Approach for Few-shot
classifiers Against Adversarial Support Samples [107.38834819682315]
We study a conceptually simple approach to defend few-shot classifiers against adversarial attacks.
We propose a simple attack-agnostic detection method, using the concept of self-similarity and filtering.
Our evaluation on the miniImagenet (MI) and CUB datasets exhibit good attack detection performance.
arXiv Detail & Related papers (2021-10-24T05:46:03Z) - MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition.
We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL)
In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
arXiv Detail & Related papers (2021-07-23T06:57:08Z) - Localized Uncertainty Attacks [9.36341602283533]
We present localized uncertainty attacks against deep learning models.
We create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.
Unlike $ell_p$ ball or functional attacks which perturb inputs indiscriminately, our targeted changes can be less perceptible.
arXiv Detail & Related papers (2021-06-17T03:07:22Z) - Towards Defending against Adversarial Examples via Attack-Invariant
Features [147.85346057241605]
Deep neural networks (DNNs) are vulnerable to adversarial noise.
adversarial robustness can be improved by exploiting adversarial examples.
Models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
arXiv Detail & Related papers (2021-06-09T12:49:54Z) - Learning to Separate Clusters of Adversarial Representations for Robust
Adversarial Detection [50.03939695025513]
We propose a new probabilistic adversarial detector motivated by a recently introduced non-robust feature.
In this paper, we consider the non-robust features as a common property of adversarial examples, and we deduce it is possible to find a cluster in representation space corresponding to the property.
This idea leads us to probability estimate distribution of adversarial representations in a separate cluster, and leverage the distribution for a likelihood based adversarial detector.
arXiv Detail & Related papers (2020-12-07T07:21:18Z) - Beyond cross-entropy: learning highly separable feature distributions
for robust and accurate classification [22.806324361016863]
We propose a novel approach for training deep robust multiclass classifiers that provides adversarial robustness.
We show that the regularization of the latent space based on our approach yields excellent classification accuracy.
arXiv Detail & Related papers (2020-10-29T11:15:17Z) - Towards Robust Fine-grained Recognition by Maximal Separation of
Discriminative Features [72.72840552588134]
We identify the proximity of the latent representations of different classes in fine-grained recognition networks as a key factor to the success of adversarial attacks.
We introduce an attention-based regularization mechanism that maximally separates the discriminative latent features of different classes.
arXiv Detail & Related papers (2020-06-10T18:34:45Z) - Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial
Perturbations [65.05561023880351]
Adversarial examples are malicious inputs crafted to induce misclassification.
This paper studies a complementary failure mode, invariance-based adversarial examples.
We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks.
arXiv Detail & Related papers (2020-02-11T18:50:23Z)
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.