{"total":80,"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":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"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":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47,"area":"diffusion"},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2312.14223","title":"Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation","created":"2023-12-21","cited_by_count":41,"area":null},{"id":"2107.10171","title":"Leave-one-out Unfairness","created":"2021-07-21","cited_by_count":36,"area":null},{"id":"2209.10117","title":"A Comprehensive Survey on Trustworthy Recommender Systems","created":"2022-09-21","cited_by_count":32,"area":null},{"id":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2308.08162","title":"Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations","created":"2023-08-16","cited_by_count":27,"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":"2106.10606","title":"Attack to Fool and Explain Deep Networks","created":"2021-06-20","cited_by_count":17,"area":null},{"id":"2207.11378","title":"Do Perceptually Aligned Gradients Imply Adversarial Robustness?","created":"2022-07-22","cited_by_count":15,"area":null},{"id":"2102.12196","title":"Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis","created":"2021-02-24","cited_by_count":13,"area":null},{"id":"2106.09534","title":"Adversarial Visual Robustness by Causal Intervention","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2306.16805","title":"CLIPAG: Towards Generator-Free Text-to-Image Generation","created":"2023-06-29","cited_by_count":12,"area":null},{"id":"2406.08958","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","created":"2024-06-13","cited_by_count":12,"area":null},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2205.04533","title":"How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?","created":"2022-05-09","cited_by_count":11,"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":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2302.13095","title":"Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts","created":"2023-02-25","cited_by_count":9,"area":null},{"id":"2303.15421","title":"ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2104.12679","title":"Impact of Spatial Frequency Based Constraints on Adversarial Robustness","created":"2021-04-26","cited_by_count":8,"area":null},{"id":"2106.08153","title":"Now You See It, Now You Dont: Adversarial Vulnerabilities in Computational Pathology","created":"2021-06-14","cited_by_count":7,"area":null},{"id":"2205.03824","title":"A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","created":"2022-05-08","cited_by_count":7,"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":"2512.13568","title":"Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability","created":"2025-12-15","cited_by_count":7,"area":"mechinterp"},{"id":"2202.00673","title":"Visualizing Automatic Speech Recognition -- Means for a Better Understanding?","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2203.10502","title":"Adversarial Parameter Attack on Deep Neural Networks","created":"2022-03-20","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":"2304.06919","title":"Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense","created":"2023-04-14","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":"2303.06302","title":"Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2303.15409","title":"Class-Conditioned Transformation for Enhanced Robust Image Classification","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2307.15786","title":"SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2312.13033","title":"Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2406.12507","title":"Improving the Evaluation and Actionability of Explanation Methods for Multivariate Time Series Classification","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2101.10562","title":"Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems","created":"2021-01-26","cited_by_count":4,"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":"2111.00295","title":"Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach","created":"2021-10-30","cited_by_count":4,"area":null},{"id":"2206.12284","title":"Robustness of Explanation Methods for NLP Models","created":"2022-06-24","cited_by_count":3,"area":null},{"id":"2505.14042","title":"Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2111.04404","title":"Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2112.03615","title":"Saliency Diversified Deep Ensemble for Robustness to Adversaries","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2207.13036","title":"Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense","created":"2022-07-09","cited_by_count":2,"area":null},{"id":"2402.10470","title":"Theoretical Understanding of Learning from Adversarial Perturbations","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2506.12284","title":"GrokAlign: Geometric Characterisation and Acceleration of Grokking","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2510.20627","title":"H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2601.18678","title":"Counterfactual Explanations on Robust Perceptual Geodesics","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2102.05096","title":"Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2307.01225","title":"Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2310.09361","title":"Is Certifying $\\ell_p$ Robustness Still Worthwhile?","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2512.03730","title":"Out-of-the-box: Black-box Causal Attacks on Object Detectors","created":"2025-12-03","cited_by_count":1,"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":"2306.16581","title":"Does Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2309.09928","title":"Evaluating Adversarial Robustness with Expected Viable Performance","created":"2023-09-18","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":"2405.01855","title":"Robust Explainable Recommendation","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2406.04933","title":"Leveraging Activations for Superpixel Explanations","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2502.16688","title":"Analyzing Factors Influencing Driver Willingness to Accept Advanced Driver Assistance Systems","created":"2025-02-23","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":"2504.05483","title":"Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability","created":"2025-04-07","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},{"id":"2509.20148","title":"Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2512.08445","title":"Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2603.07302","title":"Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2604.25315","title":"SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.02589","title":"Representation learning from OCT images","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.16362","title":"Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classifiers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.07375","title":"On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces","created":"2026-07-08","cited_by_count":0,"area":"mllm"},{"id":"2609.35890","title":"Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training","created":"2026-09-27","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}