Pixel-level Certified Explanations via Randomized Smoothing

• URL: http://arxiv.org/abs/2506.15499v1
• Date: Wed, 18 Jun 2025 14:41:24 GMT
• Title: Pixel-level Certified Explanations via Randomized Smoothing
• Authors: Alaa Anani, Tobias Lorenz, Mario Fritz, Bernt Schiele,
• Abstract summary: Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels.<n>Small, imperceptible input perturbations can drastically alter the attribution map while maintaining the same prediction.<n>We introduce the first certification framework that guarantees pixel-level robustness for any black-box attribution method.
• Score: 87.48628403354351
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the attribution map while maintaining the same prediction. This vulnerability undermines their trustworthiness and calls for rigorous robustness guarantees of pixel-level attribution scores. We introduce the first certification framework that guarantees pixel-level robustness for any black-box attribution method using randomized smoothing. By sparsifying and smoothing attribution maps, we reformulate the task as a segmentation problem and certify each pixel's importance against $\ell_2$-bounded perturbations. We further propose three evaluation metrics to assess certified robustness, localization, and faithfulness. An extensive evaluation of 12 attribution methods across 5 ImageNet models shows that our certified attributions are robust, interpretable, and faithful, enabling reliable use in downstream tasks. Our code is at https://github.com/AlaaAnani/certified-attributions.

Related papers

• Certifying Robustness of Learning-Based Keypoint Detection and Pose Estimation Methods [9.953693315812995]
  This work addresses the certification of robustness of vision-based two-stage 6D object pose estimation. The core idea is to transform the certification of local robustness into neural network verification for classification tasks.
  arXiv  Detail & Related papers  (2024-07-31T19:02:54Z)
• Trust, but Verify: Robust Image Segmentation using Deep Learning [7.220625464268644]
  We describe a method for verifying the output of a deep neural network for medical image segmentation. We show that previous methods for segmentation evaluation that do use deep neural regression networks are vulnerable to false negatives.
  arXiv  Detail & Related papers  (2023-10-25T20:55:07Z)
• Hierarchical Randomized Smoothing [94.59984692215426]
  Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs. We introduce hierarchical randomized smoothing: We partially smooth objects by adding random noise only on a randomly selected subset of their entities. We experimentally demonstrate the importance of hierarchical smoothing in image and node classification, where it yields superior robustness-accuracy trade-offs.
  arXiv  Detail & Related papers  (2023-10-24T22:24:44Z)
• The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing [85.85160896547698]
  Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. We show how to design an efficient classifier with a certified radius by relying on noise injection into the inputs. Our novel certification procedure allows us to use pre-trained models with randomized smoothing, effectively improving the current certification radius in a zero-shot manner.
  arXiv  Detail & Related papers  (2023-09-28T22:41:47Z)
• The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector [70.43599299422813]
  Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. We propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. UAED achieves superior performance consistently across multiple edge detection benchmarks.
  arXiv  Detail & Related papers  (2023-03-21T13:14:36Z)
• Smooth-Reduce: Leveraging Patches for Improved Certified Robustness [100.28947222215463]
  We propose a training-free, modified smoothing approach, Smooth-Reduce. Our algorithm classifies overlapping patches extracted from an input image, and aggregates the predicted logits to certify a larger radius around the input. We provide theoretical guarantees for such certificates, and empirically show significant improvements over other randomized smoothing methods.
  arXiv  Detail & Related papers  (2022-05-12T15:26:20Z)
• Scalable Certified Segmentation via Randomized Smoothing [9.775834440292487]
  We present a new certification method for image and point cloud segmentation based on randomized smoothing. We show that our algorithm can achieve, for the first time, competitive accuracy and certification guarantees on real-world segmentation tasks.
  arXiv  Detail & Related papers  (2021-07-01T05:52:39Z)
• Certifying Confidence via Randomized Smoothing [151.67113334248464]
  Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. Most smoothing methods do not give us any information about the confidence with which the underlying classifier makes a prediction. We propose a method to generate certified radii for the prediction confidence of the smoothed classifier.
  arXiv  Detail & Related papers  (2020-09-17T04:37:26Z)
• Detection as Regression: Certified Object Detection by Median Smoothing [50.89591634725045]
  This work is motivated by recent progress on certified classification by randomized smoothing. We obtain the first model-agnostic, training-free, and certified defense for object detection against $ell$-bounded attacks.
  arXiv  Detail & Related papers  (2020-07-07T18:40:19Z)

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.