{"total":37,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2111.01124","title":"When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?","created":"2021-11-01","cited_by_count":77,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2210.06284","title":"Visual Prompting for Adversarial Robustness","created":"2022-10-12","cited_by_count":34,"area":null},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2203.14145","title":"Reverse Engineering of Imperceptible Adversarial Image Perturbations","created":"2022-03-26","cited_by_count":17,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2203.12709","title":"Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation","created":"2022-03-23","cited_by_count":12,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2110.07305","title":"DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2205.07279","title":"Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection","created":"2022-05-15","cited_by_count":6,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2206.07842","title":"Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2211.15926","title":"Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2304.14601","title":"Improve Video Representation with Temporal Adversarial Augmentation","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2404.04662","title":"Learning Minimal Neural Specifications","created":"2024-04-06","cited_by_count":3,"area":null},{"id":"2404.10789","title":"PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2409.15190","title":"Interpretability-Guided Test-Time Adversarial Defense","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2209.04326","title":"Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2303.00340","title":"A Practical Upper Bound for the Worst-Case Attribution Deviations","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2403.06087","title":"Learning the irreversible progression trajectory of Alzheimer's disease","created":"2024-03-10","cited_by_count":2,"area":null},{"id":"2502.14572","title":"Factor Graph-based Interpretable Neural Networks","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2105.14171","title":"The Definitions of Interpretability and Learning of Interpretable Models","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2111.08701","title":"Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classification","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2209.06971","title":"PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2212.14106","title":"Provable Robust Saliency-based Explanations","created":"2022-12-28","cited_by_count":1,"area":null},{"id":"2405.06361","title":"Certified $\\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2103.07364","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2403.06013","title":"Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2412.11119","title":"Impact of Adversarial Attacks on Deep Learning Model Explainability","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2508.03780","title":"Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition","created":"2025-08-05","cited_by_count":0,"area":null}],"next_cursor":null}