{"total":19,"rows":[{"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":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2103.08187","title":"Adversarial Training is Not Ready for Robot Learning","created":"2021-03-15","cited_by_count":20,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2404.04647","title":"Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training","created":"2024-04-06","cited_by_count":7,"area":null},{"id":"2209.11549","title":"MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier","created":"2022-09-23","cited_by_count":6,"area":null},{"id":"2407.19683","title":"Revisiting the robustness of post-hoc interpretability methods","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2108.10131","title":"Improving the trustworthiness of image classification models by utilizing bounding-box annotations","created":"2021-08-15","cited_by_count":4,"area":null},{"id":"2304.13836","title":"On Pitfalls of $\\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2304.04033","title":"Exploring the Connection between Robust and Generative Models","created":"2023-04-08","cited_by_count":2,"area":null},{"id":"2607.03165","title":"Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2103.10603","title":"Noise Modulation: Let Your Model Interpret Itself","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2207.07769","title":"Anomalous behaviour in loss-gradient based interpretability methods","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2405.01849","title":"Stability of Explainable Recommendation","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2503.11160","title":"Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.12683","title":"Algebraic Adversarial Attacks on Explainability Models","created":"2025-03-16","cited_by_count":0,"area":null}],"next_cursor":null}