Research map / Adversarial robustness and security / Certified and empirical robustness
Towards Automating Model Explanations with Certified Robustness Guarantees
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 |
|---|---|---|---|
| Add the certified robust interpretability regularizer (ablation) | AutoRMI · MNIST, ϵ = 0.5 and ϵ = 1.0 | top-k intersection: 0.79±0.13 -> 0.89±0.08; 0.70±0.06 -> 0.85±0.10 | Helped |
| Add the certified robust interpretability regularizer (ablation) | AutoRMI · AT&T, ϵ = 0.5 and ϵ = 1.0 | top-k intersection: 0.69±0.09 -> 0.73±0.08; 0.62±0.08 -> 0.67±0.05 | Helped |
| Add the prototype-based interpretability regularizer (ablation) | AutoRMI · MNIST | concept representativeness | Helped |
| Remove the prototype-based interpretability regularizer (ablation) | AutoRMI · MNIST | concept representativeness | Hurt |
| Increase the number of candidate grown neurons (ablation) | AutoRMI · MNIST, AT&T, Diabetic Retinopathy, and Wine Quality | training loss | Helped |
Closest papers by meaning
- Robust Explanation for Free or At the Cost of Faithfulness (ICML 2023 · similarity 0.89)
- Towards Automatic Concept-based Explanations (NeurIPS 2019 · similarity 0.88)
- Understanding Inter-Concept Relationships in Concept-Based Models (ICML 2024 · similarity 0.87)
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.86)
- Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract) (AAAI 2024 · similarity 0.85)
- Causally Reliable Concept Bottleneck Models (NeurIPS 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.