{"total":46,"rows":[{"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"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":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"area":null},{"id":"2303.05506","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","created":"2023-03-09","cited_by_count":32,"area":null},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28,"area":null},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2101.09498","title":"Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations","created":"2021-01-23","cited_by_count":15,"area":null},{"id":"2303.16390","title":"Are Data-driven Explanations Robust against Out-of-distribution Data?","created":"2023-03-29","cited_by_count":14,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"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":"2304.08847","title":"BadVFL: Backdoor Attacks in Vertical Federated Learning","created":"2023-04-18","cited_by_count":10,"area":null},{"id":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2303.09767","title":"It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness","created":"2023-03-17","cited_by_count":9,"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":"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":"2211.15900","title":"Towards More Robust Interpretation via Local Gradient Alignment","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2310.06514","title":"AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2312.10534","title":"Rethinking Robustness of Model Attributions","created":"2023-12-16","cited_by_count":3,"area":null},{"id":"2603.15656","title":"Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2112.12444","title":"More Than Words: Towards Better Quality Interpretations of Text Classifiers","created":"2021-12-23","cited_by_count":2,"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":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","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":"2411.09776","title":"Combining Machine Learning Defenses without Conflicts","created":"2024-11-14","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":"2201.12143","title":"Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2207.05902","title":"Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations","created":"2022-07-13","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":"2212.09155","title":"Estimating the Adversarial Robustness of Attributions in Text with Transformers","created":"2022-12-18","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":"2307.02094","title":"DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications","created":"2023-07-05","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":"2603.01938","title":"Explanation-Guided Adversarial Training for Robust and Interpretable Models","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2307.04024","title":"Robust Ranking Explanations","created":"2023-07-08","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":"2403.16569","title":"Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors","created":"2024-03-25","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":"2505.12421","title":"Fixed Point Explainability","created":"2025-05-18","cited_by_count":0,"area":null},{"id":"2511.13535","title":"Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.06665","title":"Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2610.15299","title":"WisdomNet: trustable machine learning toward error-free classification","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}