{"total":236,"rows":[{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"area":null},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2111.02801","title":"Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems","created":"2021-11-01","cited_by_count":222,"area":null},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2112.08304","title":"On the Convergence and Robustness of Adversarial Training","created":"2021-12-15","cited_by_count":130,"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":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"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":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"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":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2111.01564","title":"MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks","created":"2021-11-02","cited_by_count":44,"area":null},{"id":"2203.09678","title":"Self-Ensemble Adversarial Training for Improved Robustness","created":"2022-03-18","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":"2106.04938","title":"Attacking Adversarial Attacks as A Defense","created":"2021-06-09","cited_by_count":32,"area":null},{"id":"2307.07873","title":"Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability","created":"2023-07-15","cited_by_count":32,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2104.01575","title":"Reliably fast adversarial training via latent adversarial perturbation","created":"2021-04-04","cited_by_count":29,"area":null},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2108.01289","title":"AdvRush: Searching for Adversarially Robust Neural Architectures","created":"2021-08-03","cited_by_count":28,"area":null},{"id":"2110.15317","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","created":"2021-10-28","cited_by_count":28,"area":null},{"id":"2404.19287","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","created":"2024-04-30","cited_by_count":28,"area":"mllm"},{"id":"2302.00457","title":"Simplicity Bias in 1-Hidden Layer Neural Networks","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2106.06235","title":"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks","created":"2021-06-11","cited_by_count":24,"area":null},{"id":"2109.00946","title":"Adversarial Robustness for Unsupervised Domain Adaptation","created":"2021-09-02","cited_by_count":24,"area":null},{"id":"2210.16222","title":"Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions","created":"2022-10-28","cited_by_count":24,"area":null},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23,"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":"2212.04985","title":"Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2111.13613","title":"The Geometry of Adversarial Training in Binary Classification","created":"2021-11-26","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2206.07144","title":"Efficiently Training Low-Curvature Neural Networks","created":"2022-06-14","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2407.13646","title":"Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking","created":"2024-07-18","cited_by_count":19,"area":null},{"id":"2211.14966","title":"Adversarial Rademacher Complexity of Deep Neural Networks","created":"2022-11-27","cited_by_count":18,"area":null},{"id":"2212.01806","title":"Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks","created":"2022-12-04","cited_by_count":18,"area":null},{"id":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2403.10045","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","created":"2024-03-15","cited_by_count":17,"area":null},{"id":"2102.07048","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","created":"2021-02-14","cited_by_count":16,"area":null},{"id":"2103.03438","title":"Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2110.14855","title":"CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks","created":"2021-10-28","cited_by_count":15,"area":null},{"id":"2206.09098","title":"Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification","created":"2022-06-18","cited_by_count":15,"area":null},{"id":"2207.11378","title":"Do Perceptually Aligned Gradients Imply Adversarial Robustness?","created":"2022-07-22","cited_by_count":15,"area":null},{"id":"2407.06754","title":"Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2312.15911","title":"Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection","created":"2023-12-26","cited_by_count":14,"area":null},{"id":"2108.11673","title":"Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference","created":"2021-08-26","cited_by_count":13,"area":null},{"id":"2204.11848","title":"On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning","created":"2022-04-23","cited_by_count":13,"area":null},{"id":"2209.10677","title":"NashAE: Disentangling Representations through Adversarial Covariance Minimization","created":"2022-09-21","cited_by_count":13,"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":"2105.02942","title":"Understanding Catastrophic Overfitting in Adversarial Training","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2212.08733","title":"Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ","created":"2022-12-16","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":"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":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2408.13809","title":"On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective","created":"2024-08-25","cited_by_count":11,"area":null},{"id":"2102.07244","title":"Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS","created":"2021-02-14","cited_by_count":10,"area":null},{"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":"2208.07022","title":"Memory-Driven Text-to-Image Generation","created":"2022-08-15","cited_by_count":10,"area":null},{"id":"2210.14672","title":"Sparsity in Continuous-Depth Neural Networks","created":"2022-10-26","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":"2101.03042","title":"Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective","created":"2021-01-08","cited_by_count":9,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2206.06257","title":"Distributed Adversarial Training to Robustify Deep Neural Networks at Scale","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2401.01148","title":"PAC-Bayes-Chernoff bounds for unbounded losses","created":"2024-01-02","cited_by_count":9,"area":null},{"id":"2105.14676","title":"NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2109.06294","title":"On the regularized risk of distributionally robust learning over deep neural networks","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2109.14715","title":"USIS: Unsupervised Semantic Image Synthesis","created":"2021-09-29","cited_by_count":8,"area":null},{"id":"2212.09342","title":"Explaining Classifications to Non Experts: An XAI User Study of Post Hoc Explanations for a Classifier When People Lack Expertise","created":"2022-12-19","cited_by_count":8,"area":null},{"id":"2401.11618","title":"Efficient local linearity regularization to overcome catastrophic overfitting","created":"2024-01-21","cited_by_count":8,"area":null},{"id":"2412.18952","title":"Bridging Interpretability and Robustness Using LIME-Guided Model Refinement","created":"2024-12-25","cited_by_count":8,"area":null},{"id":"2102.04450","title":"Noise Optimization for Artificial Neural Networks","created":"2021-02-06","cited_by_count":7,"area":null},{"id":"2103.13598","title":"Recent Advances in Large Margin Learning","created":"2021-03-25","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":"2211.08008","title":"MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2403.17520","title":"Boosting Adversarial Training via Fisher-Rao Norm-based Regularization","created":"2024-03-26","cited_by_count":7,"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":"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":"2102.01979","title":"Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice","created":"2021-02-03","cited_by_count":6,"area":null},{"id":"2109.00707","title":"Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study","created":"2021-09-02","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":"2201.10972","title":"How Robust are Discriminatively Trained Zero-Shot Learning Models?","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2302.02016","title":"Improving Interpretability via Explicit Word Interaction Graph Layer","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2302.14643","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","created":"2023-02-27","cited_by_count":6,"area":"distill"},{"id":"2306.07197","title":"AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation","created":"2023-06-12","cited_by_count":6,"area":null},{"id":"2401.14961","title":"Set-Based Training for Neural Network Verification","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2403.13134","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2403.18186","title":"Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting","created":"2024-03-27","cited_by_count":6,"area":null},{"id":"2406.00685","title":"Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2409.20139","title":"Characterizing Model Robustness via Natural Input Gradients","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2102.08868","title":"Bridging the Gap Between Adversarial Robustness and Optimization Bias","created":"2021-02-17","cited_by_count":5,"area":null}],"next_cursor":"100"}