{"total":39,"rows":[{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"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":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111,"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":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"area":null},{"id":"2106.02105","title":"A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2204.02735","title":"Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck","created":"2022-04-06","cited_by_count":30,"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":"2305.19101","title":"Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness","created":"2023-05-30","cited_by_count":20,"area":null},{"id":"2201.12961","title":"Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations","created":"2022-01-31","cited_by_count":18,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2207.11378","title":"Do Perceptually Aligned Gradients Imply Adversarial Robustness?","created":"2022-07-22","cited_by_count":15,"area":null},{"id":"2203.13455","title":"A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training","created":"2022-03-25","cited_by_count":13,"area":null},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"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":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2108.03702","title":"BIGRoC: Boosting Image Generation via a Robust Classifier","created":"2021-08-08","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":"2102.05110","title":"Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2106.06927","title":"Inverting Adversarially Robust Networks for Image Synthesis","created":"2021-06-13","cited_by_count":6,"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":"2409.20139","title":"Characterizing Model Robustness via Natural Input Gradients","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2306.09192","title":"DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2404.08069","title":"Persistent Classification: A New Approach to Stability of Data and Adversarial Examples","created":"2024-04-11","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":"2109.04300","title":"Energy Attack: On Transferring Adversarial Examples","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2111.14726","title":"Do Invariances in Deep Neural Networks Align with Human Perception?","created":"2021-11-29","cited_by_count":2,"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":"2402.10470","title":"Theoretical Understanding of Learning from Adversarial Perturbations","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2508.11441","title":"Informative Post-Hoc Explanations Only Exist for Simple Functions","created":"2025-08-15","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":"2103.09265","title":"Bio-inspired Robustness: A Review","created":"2021-03-16","cited_by_count":1,"area":null},{"id":"2112.15111","title":"Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers","created":"2021-12-30","cited_by_count":0,"area":null},{"id":"2204.01099","title":"Adversarially robust segmentation models learn perceptually-aligned gradients","created":"2022-04-03","cited_by_count":0,"area":null},{"id":"2310.14045","title":"Training Image Derivatives: Increased Accuracy and Universal Robustness","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2403.09863","title":"Towards White Box Deep Learning","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2507.22832","title":"Pulling Back the Curtain on Deep Networks","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2609.24260","title":"Adversarially Robust PAC Learning with Optimal VC Rates","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.07677","title":"Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}