Cover Image

When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Sridhar, Aditya
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Cryptography and Security Computer Vision and Pattern Recognition I.2.6; I.5.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
by: Chan, April, et al.
Published: (2026)

Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
by: Abdukhamidov, Eldor, et al.
Published: (2025)

TRIGS: Trojan Identification from Gradient-based Signatures
by: Hussein, Mohamed E., et al.
Published: (2023)

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors
by: Ma, Chen, et al.
Published: (2025)

A Multidisciplinary Approach to Telegram Data Analysis
by: Varbanov, Velizar, et al.
Published: (2024)

CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
by: Hong, Dasol, et al.
Published: (2025)

Localizing Adversarial Attacks To Produces More Imperceptible Noise
by: Reddy, Pavan, et al.
Published: (2025)

Riemannian-Geometric Fingerprints of Generative Models
by: Song, Hae Jin, et al.
Published: (2025)

How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?
by: Costa, Daniel da Silva, et al.
Published: (2026)

BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
by: Cheng, He, et al.
Published: (2024)

CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
by: Nishiyama, Daiki, et al.
Published: (2022)

Ternary Decision Trees with Locally-Adaptive Uncertainty Zones
by: Smits, William
Published: (2026)

A Boundary-Aware Non-parametric Granular-Ball Classifier Based on Minimum Description Length
by: Xian, Zeqiang, et al.
Published: (2026)

RobustModelMaker: Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning
by: Barnard, Amanda S
Published: (2026)

Density-aware Sample-specific Attack
by: Wang, Qiyuan, et al.
Published: (2026)

Spiking Neural Networks for event-based action recognition: A new task to understand their advantage
by: Vicente-Sola, Alex, et al.
Published: (2022)

Signal-Based Malware Classification Using 1D CNNs
by: Wilkie, Jack, et al.
Published: (2025)

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks
by: Feng, Zhou, et al.
Published: (2025)

A Spatio-Temporal Deep Learning Approach For High-Resolution Gridded Monsoon Prediction
by: Borah, Parashjyoti, et al.
Published: (2026)

Modeling the Neonatal Brain Development Using Implicit Neural Representations
by: Bieder, Florentin, et al.
Published: (2024)

Interpreting Structured Perturbations in Image Protection Methods for Diffusion Models
by: Martin, Michael R., et al.
Published: (2025)

Non-Adaptive Adversarial Face Generation
by: Kim, Sunpill, et al.
Published: (2025)

NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs
by: Miličević, Davorin, et al.
Published: (2025)

When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning
by: Steier, Joshua
Published: (2026)

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
by: Xu, Binyan, et al.
Published: (2025)

Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
by: Xu, Xinjie, et al.
Published: (2025)

Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
by: Pozdnyakov, Vitaliy, et al.
Published: (2024)

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
by: Lelle, Travis
Published: (2026)

On the Development of Binary Classification Algorithm Based on Principles of Geometry and Statistical Inference
by: Srivastava, Vatsal
Published: (2025)

MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance
by: Dong, Yi, et al.
Published: (2025)

Closing the Distribution Gap in Adversarial Training for LLMs
by: Hu, Chengzhi, et al.
Published: (2026)

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
by: Cullen, Andrew C., et al.
Published: (2023)

Generalizable and Interpretable RF Fingerprinting with Shapelet-Enhanced Large Language Models
by: Zhao, Tianya, et al.
Published: (2026)

CASE: Contrastive Activation for Saliency Estimation
by: Williamson, Dane, et al.
Published: (2025)

Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
by: Fernandez, David, et al.
Published: (2026)

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
by: Xu, Binyan, et al.
Published: (2025)

NeuroViz: Real-time Interactive Visualization of Forward and Backward Passes in Neural Network Training
by: Sharma, Tanvi, et al.
Published: (2026)

ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings
by: Poorna, Rajas, et al.
Published: (2026)

Semantically Guided Adversarial Testing of Vision Models Using Language Models
by: Filus, Katarzyna, et al.
Published: (2025)

Scalable Deep Subspace Clustering Network
by: Mrabah, Nairouz, et al.
Published: (2025)