Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis

• URL: http://arxiv.org/abs/2203.16141v1
• Date: Wed, 30 Mar 2022 08:28:48 GMT
• Title: Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
• Authors: Yi Chang, Zhao Ren, Thanh Tam Nguyen, Wolfgang Nejdl, Bj\"orn W. Schuller
• Abstract summary: We develop a unified example-based explanation method for selecting both representative data (prototypes) and outliers (criticisms) In particular, we propose a novel application of adversarial attacks to generate an explanation spectrum of data instances via an iterative fast gradient sign method.
• Score: 15.983890739091159
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19. To facilitate the interpretability of classification results, especially ones based on deep learning, many explanation methods have been proposed using prototypes. However, existing explanation techniques often assume that the data is non-biased and the prediction results can be explained by a set of prototypical examples. In this work, we develop a unified example-based explanation method for selecting both representative data (prototypes) and outliers (criticisms). In particular, we propose a novel application of adversarial attacks to generate an explanation spectrum of data instances via an iterative fast gradient sign method. Such unified explanation can avoid over-generalisation and bias by allowing human experts to assess the model mistakes case by case. We performed a wide range of quantitative and qualitative evaluations to show that our approach generates effective and understandable explanation and is robust with many deep learning models

Related papers

• Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information [75.36597470578724]
  Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. We propose gUided Purification (COUP) algorithm, which purifies while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods.
  arXiv  Detail & Related papers  (2024-08-12T02:48:00Z)
• Analyzing the Influence of Training Samples on Explanations [5.695152528716705]
  We propose a novel problem of identifying training data samples that have a high influence on a given explanation. For this, we propose an algorithm that identifies such influential training samples.
  arXiv  Detail & Related papers  (2024-06-05T07:20:06Z)
• Enhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypes [7.633493982907541]
  We propose a novel interpretable-by-design method, ProtoVerse, to find relevant sub-parts of vertebral fractures (prototypes) that reliably explain the model's decision in a human-understandable way. We have experimented with the VerSe'19 dataset and outperformed the existing prototype-based method.
  arXiv  Detail & Related papers  (2024-04-03T16:04:59Z)
• Towards Generating Adversarial Examples on Mixed-type Data [32.41305735919529]
  We propose a novel attack algorithm M-Attack, which can effectively generate adversarial examples in mixed-type data. Based on M-Attack, attackers can attempt to mislead the targeted classification model's prediction, by only slightly perturbing both the numerical and categorical features in the given data samples. Our generated adversarial examples can evade potential detection models, which makes the attack indeed insidious.
  arXiv  Detail & Related papers  (2022-10-17T20:17:21Z)
• Learning from Multiple Expert Annotators for Enhancing Anomaly Detection in Medical Image Analysis [0.31317409221921133]
  In medical imaging analysis, multiple expert annotators often produce subjective estimates about "ground truth labels" We propose a simple yet effective approach to combine annotations from multiple radiology experts for training a deep learning-based detector.
  arXiv  Detail & Related papers  (2022-03-20T17:57:26Z)
• 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)
• Unsupervised Detection of Adversarial Examples with Model Explanations [0.6091702876917279]
  We propose a simple yet effective method to detect adversarial examples using methods developed to explain the model's behavior. Our evaluations with MNIST handwritten dataset show that our method is capable of detecting adversarial examples with high confidence.
  arXiv  Detail & Related papers  (2021-07-22T06:54:18Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier [121.6758865857686]
  We investigate the transferability of adversarial examples for text classification models. We propose a genetic algorithm to find an ensemble of models that can induce adversarial examples to fool almost all existing models. We derive word replacement rules that can be used for model diagnostics from these adversarial examples.
  arXiv  Detail & Related papers  (2020-11-17T10:45:05Z)
• Toward Scalable and Unified Example-based Explanation and Outlier Detection [128.23117182137418]
  We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction. We show that our prototype-based networks beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy.
  arXiv  Detail & Related papers  (2020-11-11T05:58:17Z)
• Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
  We establish a novel set of evaluation criteria for such feature based explanations by analysis. We obtain new explanations that are loosely necessary and sufficient for a prediction. We extend the explanation to extract the set of features that would move the current prediction to a target class.
  arXiv  Detail & Related papers  (2020-05-31T05:52:05Z)

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.