{"total":75,"rows":[{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"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":"2202.01181","title":"Make Some Noise: Reliable and Efficient Single-Step Adversarial Training","created":"2022-02-02","cited_by_count":43,"area":null},{"id":"2111.12229","title":"Subspace Adversarial Training","created":"2021-11-24","cited_by_count":41,"area":null},{"id":"2110.05007","title":"Boosting Fast Adversarial Training with Learnable Adversarial Initialization","created":"2021-10-11","cited_by_count":40,"area":null},{"id":"2207.08859","title":"Prior-Guided Adversarial Initialization for Fast Adversarial Training","created":"2022-07-18","cited_by_count":35,"area":null},{"id":"2304.00202","title":"Improving Fast Adversarial Training with Prior-Guided Knowledge","created":"2023-04-01","cited_by_count":35,"area":null},{"id":"2207.10498","title":"Towards Efficient Adversarial Training on Vision Transformers","created":"2022-07-21","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":"2211.11056","title":"Safe Control Under Input Limits with Neural Control Barrier Functions","created":"2022-11-20","cited_by_count":29,"area":null},{"id":"2204.00491","title":"FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting","created":"2022-04-01","cited_by_count":28,"area":null},{"id":"2206.02417","title":"Fast Adversarial Training with Adaptive Step Size","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2211.00525","title":"The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training","created":"2022-11-01","cited_by_count":23,"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":"2310.08847","title":"On the Over-Memorization During Natural, Robust and Catastrophic Overfitting","created":"2023-10-13","cited_by_count":20,"area":null},{"id":"2212.05680","title":"REAP: A Large-Scale Realistic Adversarial Patch Benchmark","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2103.15476","title":"ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training","created":"2021-03-29","cited_by_count":15,"area":null},{"id":"2308.11443","title":"Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging","created":"2023-08-22","cited_by_count":14,"area":null},{"id":"2308.12857","title":"Fast Adversarial Training with Smooth Convergence","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2302.12366","title":"Less is More: Data Pruning for Faster Adversarial Training","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2407.12443","title":"Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective","created":"2024-07-17","cited_by_count":13,"area":null},{"id":"2105.02942","title":"Understanding Catastrophic Overfitting in Adversarial Training","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2404.08154","title":"Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization","created":"2024-04-11","cited_by_count":12,"area":null},{"id":"2405.16262","title":"Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2302.10181","title":"Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2504.14921","title":"Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos","created":"2025-04-21","cited_by_count":9,"area":null},{"id":"2310.15444","title":"Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks","created":"2023-10-24","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":"2502.04573","title":"Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2202.05488","title":"Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign","created":"2022-02-11","cited_by_count":7,"area":null},{"id":"2401.10359","title":"Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2403.11448","title":"Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM","created":"2024-03-18","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":"2410.15042","title":"Adversarial Training: A Survey","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2302.11963","title":"Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2404.08980","title":"Stability and Generalization in Free Adversarial Training","created":"2024-04-13","cited_by_count":5,"area":null},{"id":"2106.15357","title":"Multi-stage Optimization based Adversarial Training","created":"2021-06-26","cited_by_count":4,"area":null},{"id":"2405.05075","title":"Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2407.15385","title":"Towards Robust Vision Transformer via Masked Adaptive Ensemble","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2108.11135","title":"Bridged Adversarial Training","created":"2021-08-25","cited_by_count":3,"area":null},{"id":"2410.01617","title":"On Using Certified Training towards Empirical Robustness","created":"2024-10-02","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":"2103.01400","title":"Smoothness Analysis of Adversarial Training","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2108.13239","title":"Adaptive perturbation adversarial training: based on reinforcement learning","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2206.08242","title":"Catastrophic overfitting can be induced with discriminative non-robust features","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2209.02684","title":"Bag of Tricks for FGSM Adversarial Training","created":"2022-09-06","cited_by_count":2,"area":null},{"id":"2409.17589","title":"Improving Fast Adversarial Training via Self-Knowledge Guidance","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2502.11858","title":"Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.22486","title":"Understanding Adversarial Training with Energy-based Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2106.15998","title":"Single-Step Adversarial Training for Semantic Segmentation","created":"2021-06-30","cited_by_count":1,"area":null},{"id":"2203.07138","title":"Adversarial amplitude swap towards robust image classifiers","created":"2022-03-14","cited_by_count":1,"area":null},{"id":"2308.06612","title":"On the Interplay of Convolutional Padding and Adversarial Robustness","created":"2023-08-12","cited_by_count":1,"area":null},{"id":"2309.17348","title":"Intrinsic Biologically Plausible Adversarial Robustness","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2409.20517","title":"SMLE: Safe Machine Learning via Embedded Overapproximation","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2505.02360","title":"Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2604.22853","title":"FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2604.24332","title":"Mitigating Error Amplification in Fast Adversarial Training","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2210.05373","title":"Stable and Efficient Adversarial Training through Local Linearization","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2301.01343","title":"Explainability and Robustness of Deep Visual Classification Models","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2304.03955","title":"Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2305.08439","title":"Exploiting Frequency Spectrum of Adversarial Images for General Robustness","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2307.09804","title":"Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2312.02236","title":"Rethinking Adversarial Training with Neural Tangent Kernel","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2406.04070","title":"Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2408.03944","title":"Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2502.21041","title":"Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2506.05032","title":"Identifying and Understanding Cross-Class Features in Adversarial Training","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.22602","title":"Are Fast Methods Stable in Adversarially Robust Transfer Learning?","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2510.05317","title":"RegMix: Adversarial Mutual and Generalization Regularization for Enhancing DNN Robustness","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2511.07208","title":"SMiLE: Provably Enforcing Global Relational Properties in Neural Networks","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2601.13645","title":"Quadratic Upper Bound for Boosting Robustness","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.05583","title":"WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.24350","title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.00738","title":"SORA: Free Second-Order Attacks in Fast Adversarial Training","created":"2026-05-30","cited_by_count":0,"area":null}],"next_cursor":null}