The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

• URL: http://arxiv.org/abs/2606.14466v1
• Date: Fri, 12 Jun 2026 13:58:34 GMT
• Title: The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions
• Abstract summary: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection.<n>We introduce a psychoacoustic framework that optimize inaudible perturbations to decouple model attributions from final classifications.
• Score: 0.10923877073891443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to decouple model attributions from final classifications. We evaluate this vulnerability across state-of-the-art architectures under strict prediction-preserving constraints. By evaluating the manipulation cost through domain-specific perceptual audio quality metrics alongside explanation alignment criteria, our framework demonstrates that an adversary can systematically distort automated explanation heatmaps while preserving the predicted deepfake label. Full code available at: https://github.com/cncPomper/Audio-XAI

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations [16.51678229294975]
  We propose a multi-axis evaluation framework tailored for structured audio descriptions.<n>We evaluate outputs across five axes: tag-sets, descriptions, logical reasoning, numeric measurements, and spectral profiles.<n>Our results demonstrate that this framework successfully distinguishes meaning-preserving paraphrases from genuine semantic and acoustic corruptions.
  arXiv  Detail & Related papers  (2026-07-23T15:26:52Z)
• APEX: Audio Prototype EXplanations for Classification Tasks [4.385522611751555]
  APEX (Audio Prototype EXplanations) is a framework for interpreting pre-trained audio classifiers.<n>It disentangles explanations into four perspectives: Square-based prototypes to localize transient events, Time-based for temporal patterns, Frequency-based highlighting spectral bands, and Time-Frequency-based integrating both.<n>It provides greater semantic clarity than standard gradient-based methods.
  arXiv  Detail & Related papers  (2026-05-11T08:00:38Z)
• Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference [0.0]
  Collaborative inference of object classification Deep neural Networks (DNNs) are becoming a key enabler of edge-AI.<n>In this paper, we propose a semi-gray-box and noise- aware anomaly detection framework fueled by a variational autoencoder (VAE) to capture deviations caused by adversarial manipulation.<n>The proposed framework incorporates a robust noise-aware feature that captures the characteristic behavior of environmental noise to improve detection accuracy while reducing false alarm rates.
  arXiv  Detail & Related papers  (2026-03-18T16:53:58Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• A Framework for Evaluating Faithfulness in Explainable AI for Machine Anomalous Sound Detection Using Frequency-Band Perturbation [37.2521660642532]
  We introduce a new quantitative framework for evaluating XAI faithfulness in machine-sound analysis.<n>We show that XAI techniques differ in reliability, with Occlusion demonstrating the strongest alignment with true model sensitivity.
  arXiv  Detail & Related papers  (2026-01-26T23:06:50Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching [8.466707742593078]
  Speech deepfakes are synthetic audio signals that can imitate target speakers' voices.<n>Existing methods for detecting speech deepfakes rely on supervised learning.<n>We introduce a novel interpretable one-class detection framework, which reframes speech deepfake detection as an anomaly detection task.
  arXiv  Detail & Related papers  (2025-03-23T11:15:22Z)
• Conformal Prediction of Classifiers with Many Classes based on Noisy Labels [22.841631892273547]
  Conformal Prediction (CP) controls the prediction uncertainty of classification systems.<n>We show how we can estimate the noise-free conformal threshold based on the noisy labeled data.<n>We dub our approach Noise-Aware Conformal Prediction (NACP)
  arXiv  Detail & Related papers  (2025-01-22T09:35:58Z)
• 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)
• Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection [54.20974251478516]
  We propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting. When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. Our method can easily be generalized to related fields, like speech emotion recognition.
  arXiv  Detail & Related papers  (2023-08-07T05:05:49Z)
• Consistency Regularization for Certified Robustness of Smoothed Classifiers [89.72878906950208]
  A recent technique of randomized smoothing has shown that the worst-case $ell$-robustness can be transformed into the average-case robustness. We found that the trade-off between accuracy and certified robustness of smoothed classifiers can be greatly controlled by simply regularizing the prediction consistency over noise.
  arXiv  Detail & Related papers  (2020-06-07T06:57:43Z)
• Unsupervised Domain Adaptation for Acoustic Scene Classification Using Band-Wise Statistics Matching [69.24460241328521]
  Machine learning algorithms can be negatively affected by mismatches between training (source) and test (target) data distributions. We propose an unsupervised domain adaptation method that consists of aligning the first- and second-order sample statistics of each frequency band of target-domain acoustic scenes to the ones of the source-domain training dataset. We show that the proposed method outperforms the state-of-the-art unsupervised methods found in the literature in terms of both source- and target-domain classification accuracy.
  arXiv  Detail & Related papers  (2020-04-30T23:56:05Z)

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.