Research map / Adversarial robustness and security / Certified and empirical robustness
Attribution-Based Confidence Metric For Deep Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ABC confidence on out-of-distribution inputs (FashionMNIST, notMNIST) versus MNIST | MNIST classifier with ABC · MNIST vs FashionMNIST/notMNIST | fraction of data with ABC > 0.85: 70% vs 19% (FashionMNIST), 26% (notMNIST) | Helped |
| use DeepSHAP or Integrated Gradients instead of plain gradients as attribution in ABC (ablation) | ABC metric · FashionMNIST/notMNIST vs MNIST | confidence separation (CDF) | Helped |
| increase rotation angle of MNIST inputs from 0 to 50 degrees | ABC metric · rotated MNIST | ABC and accuracy | Mixed |
Closest papers by meaning
- A Practical Upper Bound for the Worst-Case Attribution Deviations (CVPR 2023 · similarity 0.87)
- $\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models (NeurIPS 2023 · similarity 0.87)
- Rethinking Robustness of Model Attributions (AAAI 2024 · similarity 0.86)
- Towards Trustworthy Deep Learning (AAAI 2024 · similarity 0.85)
- MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks (AAAI 2024 · similarity 0.85)
- Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.