Research map / Learning theory and algorithms / Prediction and decision losses
Explanations can be manipulated and geometry is to blame
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 |
|---|---|---|---|
| optimize imperceptible input perturbation toward a target explanation | VGG-16 explanations (Gradient, LRP, PA, etc.) · ImageNet | explanation similarity to target (SSIM/PCC/MSE) | Helped |
| compute explanations with beta-smoothing (softplus with small beta) | VGG-16 explanations · ImageNet manipulated images | robustness to manipulation | Helped |
| beta-smoothing instead of SmoothGrad | explanation methods · ImageNet manipulated images | robustness | No clear effect |
| beta-smoothing instead of SmoothGrad | explanation methods · ImageNet | computational cost | Helped |
Closest papers by meaning
- Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations (ICML 2025 · similarity 0.87)
- Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable? (ICLR 2025 · similarity 0.86)
- Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · similarity 0.86)
- Factor Graph-based Interpretable Neural Networks (ICLR 2025 · similarity 0.85)
- Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs (ICML 2025 · similarity 0.85)
- Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs (ICLR 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.