Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
cs.LG, cs.AI
Submitted: 2026-09-29
Updated: 2026-10-14
Terminology
Sources
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- On Evaluating Adversarial Robustness
- Editable Concept Bottleneck Models
- Probabilistic Concept Bottleneck Models
- C-SENN: Contrastive Self-Explaining Neural Network
- Intriguing properties of neural networks
- Post-hoc Concept Bottleneck Models
- SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks