{"total":112,"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":"2103.08896","title":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation","created":"2021-03-16","cited_by_count":134,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"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":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41,"area":null},{"id":"2405.04825","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","created":"2024-05-08","cited_by_count":40,"area":"safety"},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2110.03109","title":"Consistent Counterfactuals for Deep Models","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2111.08230","title":"Selective Ensembles for Consistent Predictions","created":"2021-11-16","cited_by_count":23,"area":null},{"id":"2208.03608","title":"Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value","created":"2022-08-07","cited_by_count":23,"area":null},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"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":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2405.09800","title":"Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2406.03193","title":"Graph Neural Network Explanations are Fragile","created":"2024-06-05","cited_by_count":19,"area":null},{"id":"2108.03388","title":"Jointly Attacking Graph Neural Network and its Explanations","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2301.09559","title":"SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]","created":"2023-01-23","cited_by_count":18,"area":null},{"id":"2301.02437","title":"Valid P-Value for Deep Learning-Driven Salient Region","created":"2023-01-06","cited_by_count":17,"area":null},{"id":"2104.02768","title":"Robust Semantic Interpretability: Revisiting Concept Activation Vectors","created":"2021-04-06","cited_by_count":16,"area":null},{"id":"2105.12837","title":"Fooling Partial Dependence via Data Poisoning","created":"2021-05-26","cited_by_count":16,"area":"safety"},{"id":"2203.02586","title":"Concept-based Explanations for Out-Of-Distribution Detectors","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15,"area":null},{"id":"2103.14332","title":"Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation","created":"2021-03-26","cited_by_count":12,"area":null},{"id":"2204.04890","title":"Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2212.04454","title":"XRand: Differentially Private Defense against Explanation-Guided Attacks","created":"2022-12-08","cited_by_count":11,"area":null},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2107.01561","title":"Certifiably Robust Interpretation via Renyi Differential Privacy","created":"2021-07-04","cited_by_count":10,"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":"2307.15007","title":"Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2301.04041","title":"Manifold Restricted Interventional Shapley Values","created":"2023-01-10","cited_by_count":9,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2306.13885","title":"Manipulation Risks in Explainable AI: The Implications of the Disagreement Problem","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2106.15820","title":"Explanation-Guided Diagnosis of Machine Learning Evasion Attacks","created":"2021-06-30","cited_by_count":6,"area":null},{"id":"2111.04303","title":"Defense Against Explanation Manipulation","created":"2021-11-08","cited_by_count":6,"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":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2101.11702","title":"Better sampling in explanation methods can prevent dieselgate-like deception","created":"2021-01-26","cited_by_count":5,"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":"2302.05294","title":"MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope","created":"2023-01-08","cited_by_count":5,"area":null},{"id":"2404.18702","title":"Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2406.06417","title":"Explainable Graph Neural Networks Under Fire","created":"2024-06-10","cited_by_count":5,"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":"2601.20815","title":"GNN Explanations that do not Explain and How to find Them","created":"2026-01-28","cited_by_count":5,"area":null},{"id":"2204.09498","title":"Backdooring Explainable Machine Learning","created":"2022-04-20","cited_by_count":4,"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":"2212.03095","title":"Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2404.01964","title":"CAM-Based Methods Can See through Walls","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2108.13930","title":"EG-Booster: Explanation-Guided Booster of ML Evasion Attacks","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2202.11797","title":"Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2205.09620","title":"Towards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Data","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2306.06716","title":"On Minimizing the Impact of Dataset Shifts on Actionable Explanations","created":"2023-06-11","cited_by_count":3,"area":null},{"id":"2310.17945","title":"A Comprehensive and Reliable Feature Attribution Method: Double-sided Remove and Reconstruct (DoRaR)","created":"2023-10-27","cited_by_count":3,"area":null},{"id":"2311.04813","title":"Be Careful When Evaluating Explanations Regarding Ground Truth","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2503.08636","title":"Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2201.05071","title":"Evaluation of Neural Networks Defenses and Attacks using NDCG and Reciprocal Rank Metrics","created":"2022-01-10","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":"2403.03773","title":"Verified Training for Counterfactual Explanation Robustness under Data Shift","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2408.01715","title":"Joint Universal Adversarial Perturbations with Interpretations","created":"2024-08-03","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2102.11010","title":"Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2209.08453","title":"EMaP: Explainable AI with Manifold-based Perturbations","created":"2022-09-18","cited_by_count":1,"area":null},{"id":"2210.17130","title":"BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models","created":"2022-10-31","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":"2307.06484","title":"Single-Class Target-Specific Attack against Interpretable Deep Learning Systems","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2403.06961","title":"Explainable Transformer Prototypes for Medical Diagnoses","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2505.24729","title":"Feature Attribution from First Principles","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.08514","title":"DiffGradCAM: A Class Activation Map Using the Full Model Decision to Solve Unaddressed Adversarial Attacks","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2605.16651","title":"Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2110.01736","title":"AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operators","created":"2021-10-04","cited_by_count":0,"area":null},{"id":"2203.03729","title":"Robustness and Usefulness in AI Explanation Methods","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2307.03305","title":"A Vulnerability of Attribution Methods Using Pre-Softmax Scores","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2307.04024","title":"Robust Ranking Explanations","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2309.03638","title":"Beyond XAI:Obstacles Towards Responsible AI","created":"2023-09-07","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":"2403.10476","title":"Approximate Nullspace Augmented Finetuning for Robust Vision Transformers","created":"2024-03-15","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}],"next_cursor":"100"}