{"total":60,"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":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2104.00950","title":"Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey","created":"2021-04-02","cited_by_count":72,"area":null},{"id":"2303.09051","title":"Robust Evaluation of Diffusion-Based Adversarial Purification","created":"2023-03-16","cited_by_count":65,"area":null},{"id":"2103.01208","title":"Mind the box: $l_1$-APGD for sparse adversarial attacks on image classifiers","created":"2021-03-01","cited_by_count":51,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"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":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37,"area":null},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2101.06639","title":"Removing Undesirable Feature Contributions Using Out-of-Distribution Data","created":"2021-01-17","cited_by_count":23,"area":null},{"id":"2105.12508","title":"Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers","created":"2021-05-26","cited_by_count":23,"area":null},{"id":"2206.09880","title":"Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2106.04260","title":"Provably Robust Detection of Out-of-distribution Data (almost) for free","created":"2021-06-08","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":"2209.15246","title":"Your Out-of-Distribution Detection Method is Not Robust!","created":"2022-09-30","cited_by_count":16,"area":null},{"id":"2401.16352","title":"Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2106.09467","title":"Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2206.07314","title":"Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack","created":"2022-06-15","cited_by_count":13,"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":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2110.07305","title":"DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks","created":"2021-10-14","cited_by_count":10,"area":null},{"id":"2309.05145","title":"Outlier Robust Adversarial Training","created":"2023-09-10","cited_by_count":10,"area":null},{"id":"2502.11725","title":"Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2207.04129","title":"How many perturbations break this model? Evaluating robustness beyond adversarial accuracy","created":"2022-07-08","cited_by_count":9,"area":null},{"id":"2505.01267","title":"Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain","created":"2025-05-02","cited_by_count":8,"area":null},{"id":"2111.01714","title":"Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks","created":"2021-11-02","cited_by_count":7,"area":null},{"id":"2402.01879","title":"$\\sigma$-zero: Gradient-based Optimization of $\\ell_0$-norm Adversarial Examples","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2211.12713","title":"Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles","created":"2022-11-23","cited_by_count":6,"area":null},{"id":"2404.05219","title":"Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey","created":"2024-04-08","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},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2210.02191","title":"On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2310.12793","title":"OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2410.12607","title":"Low-Rank Adversarial PGD Attack","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2403.05100","title":"Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume","created":"2024-03-08","cited_by_count":3,"area":null},{"id":"2503.02169","title":"One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy","created":"2025-03-04","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":"2304.09875","title":"GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models","created":"2023-04-19","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":"2506.03355","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.00670","title":"Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions","created":"2025-07-01","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":"2302.09190","title":"Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2303.12481","title":"Revisiting DeepFool: generalization and improvement","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2306.16614","title":"Group-based Robustness: A General Framework for Customized Robustness in the Real World","created":"2023-06-29","cited_by_count":1,"area":null},{"id":"2411.00274","title":"Adaptive Residual Transformation for Enhanced Feature-Based OOD Detection in SAR Imagery","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.07251","title":"MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2510.13872","title":"Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2108.10066","title":"Dynamic Neural Network Architectural and Topological Adaptation and Related Methods -- A Survey","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2206.00924","title":"FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2212.07283","title":"Generative Robust Classification","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2502.17972","title":"Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2502.19755","title":"HALO: Robust Out-of-Distribution Detection via Joint Optimisation","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2601.16205","title":"Counterfactual Training: Teaching Models Plausible and Actionable Explanations","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2607.19855","title":"Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":null}