{"total":149,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"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":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74,"area":null},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2106.06168","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","created":"2021-06-11","cited_by_count":42,"area":"distill"},{"id":"2112.13547","title":"PRIME: A few primitives can boost robustness to common corruptions","created":"2021-12-27","cited_by_count":40,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39,"area":null},{"id":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39,"area":null},{"id":"2303.09495","title":"Among Us: Adversarially Robust Collaborative Perception by Consensus","created":"2023-03-16","cited_by_count":37,"area":null},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2303.10653","title":"Randomized Adversarial Training via Taylor Expansion","created":"2023-03-19","cited_by_count":28,"area":null},{"id":"2110.02180","title":"Noisy Feature Mixup","created":"2021-10-05","cited_by_count":27,"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":"2308.00313","title":"Zero-Shot Learning by Harnessing Adversarial Samples","created":"2023-08-01","cited_by_count":24,"area":null},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23,"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":"2308.02533","title":"Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning","created":"2023-08-01","cited_by_count":23,"area":null},{"id":"2106.02734","title":"Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2405.01461","title":"SATO: Stable Text-to-Motion Framework","created":"2024-05-02","cited_by_count":20,"area":null},{"id":"2106.13805","title":"Self-training Converts Weak Learners to Strong Learners in Mixture Models","created":"2021-06-25","cited_by_count":19,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2301.12554","title":"Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing","created":"2023-01-29","cited_by_count":18,"area":null},{"id":"2205.09619","title":"Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification","created":"2022-05-19","cited_by_count":16,"area":null},{"id":"2311.15551","title":"Instruct2Attack: Language-Guided Semantic Adversarial Attacks","created":"2023-11-27","cited_by_count":16,"area":null},{"id":"2312.02592","title":"FRAPPE: A Group Fairness Framework for Post-Processing Everything","created":"2023-12-05","cited_by_count":16,"area":null},{"id":"2402.02263","title":"MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers","created":"2024-02-03","cited_by_count":16,"area":null},{"id":"2108.02883","title":"Interpolation can hurt robust generalization even when there is no noise","created":"2021-08-05","cited_by_count":15,"area":null},{"id":"2203.02006","title":"Why adversarial training can hurt robust accuracy","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2206.01367","title":"Adversarial Unlearning: Reducing Confidence Along Adversarial Directions","created":"2022-06-03","cited_by_count":14,"area":"safety"},{"id":"2210.12030","title":"Evolution of Neural Tangent Kernels under Benign and Adversarial Training","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2303.13813","title":"Generalist: Decoupling Natural and Robust Generalization","created":"2023-03-24","cited_by_count":14,"area":null},{"id":"2310.18477","title":"Understanding and Improving Ensemble Adversarial Defense","created":"2023-10-27","cited_by_count":14,"area":null},{"id":"2306.01429","title":"A Closer Look at the Adversarial Robustness of Deep Equilibrium Models","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2401.01764","title":"Understanding the Detrimental Class-level Effects of Data Augmentation","created":"2023-12-07","cited_by_count":13,"area":null},{"id":"2412.12000","title":"CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception","created":"2024-12-16","cited_by_count":13,"area":null},{"id":"2508.17456","title":"Adversarial Examples Are Not Bugs, They Are Superposition","created":"2025-08-24","cited_by_count":13,"area":null},{"id":"2110.04328","title":"Distinguishing rule- and exemplar-based generalization in learning systems","created":"2021-10-08","cited_by_count":12,"area":null},{"id":"2201.13329","title":"Can Adversarial Training Be Manipulated By Non-Robust Features?","created":"2022-01-31","cited_by_count":12,"area":null},{"id":"2205.14230","title":"Semi-supervised Semantics-guided Adversarial Training for Trajectory Prediction","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2405.00256","title":"ASAM: Boosting Segment Anything Model with Adversarial Tuning","created":"2024-05-01","cited_by_count":12,"area":null},{"id":"2112.15250","title":"Benign Overfitting in Adversarially Robust Linear Classification","created":"2021-12-31","cited_by_count":11,"area":null},{"id":"2208.13893","title":"Data Isotopes for Data Provenance in DNNs","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2502.08991","title":"Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2502.16184","title":"Robustness and Cybersecurity in the EU Artificial Intelligence Act","created":"2025-02-22","cited_by_count":11,"area":null},{"id":"2103.09947","title":"Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition","created":"2021-03-17","cited_by_count":10,"area":null},{"id":"2104.09437","title":"Provable Robustness of Adversarial Training for Learning Halfspaces with Noise","created":"2021-04-19","cited_by_count":10,"area":null},{"id":"2112.06323","title":"Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses","created":"2021-12-12","cited_by_count":10,"area":null},{"id":"2304.03370","title":"Reliable learning in challenging environments","created":"2023-04-06","cited_by_count":10,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2307.13149","title":"Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions","created":"2023-07-24","cited_by_count":10,"area":null},{"id":"2203.04713","title":"Defending Black-box Skeleton-based Human Activity Classifiers","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2210.08906","title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2211.15762","title":"Understanding the Impact of Adversarial Robustness on Accuracy Disparity","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2308.15094","title":"Group-Conditional Conformal Prediction via Quantile Regression Calibration for Crop and Weed Classification","created":"2023-08-29","cited_by_count":9,"area":null},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2410.04968","title":"Collaboration! Towards Robust Neural Methods for Routing Problems","created":"2024-10-07","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":"2210.12606","title":"Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2305.16444","title":"Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2104.04886","title":"Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach","created":"2021-04-11","cited_by_count":7,"area":null},{"id":"2211.11312","title":"Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2302.01056","title":"Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2308.16454","title":"Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2311.01420","title":"Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2402.05674","title":"A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs","created":"2024-02-08","cited_by_count":7,"area":null},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2205.01947","title":"EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2306.02948","title":"Learning under random distributional shifts","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","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":"2402.12187","title":"Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2406.11206","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2103.13905","title":"StyleLess layer: Improving robustness for real-world driving","created":"2021-03-25","cited_by_count":4,"area":null},{"id":"2105.08037","title":"Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximation","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2203.13277","title":"A Manifold View of Adversarial Risk","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2209.07235","title":"Sound and Complete Verification of Polynomial Networks","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2402.04644","title":"LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views","created":"2024-02-07","cited_by_count":4,"area":null},{"id":"2409.03734","title":"Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entry","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2410.16073","title":"On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2206.03727","title":"Wavelet Regularization Benefits Adversarial Training","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2210.01288","title":"Strength-Adaptive Adversarial Training","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2305.15835","title":"PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2402.08768","title":"Adversarially Robust Feature Learning for Breast Cancer Diagnosis","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2412.04245","title":"Intriguing Properties of Robust Classification","created":"2024-12-05","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":"2508.02186","title":"Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2510.14231","title":"When Flatness Does (Not) Guarantee Adversarial Robustness","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2111.01996","title":"Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2204.13232","title":"Adversarial Fine-tune with Dynamically Regulated Adversary","created":"2022-04-28","cited_by_count":2,"area":null},{"id":"2206.13405","title":"Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2301.06871","title":"Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks","created":"2023-01-17","cited_by_count":2,"area":"diffusion"},{"id":"2305.12219","title":"Collaborative Development of NLP models","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2307.16331","title":"Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks","created":"2023-07-30","cited_by_count":2,"area":null},{"id":"2311.13656","title":"Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization","created":"2023-11-22","cited_by_count":2,"area":null},{"id":"2311.15165","title":"Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off","created":"2023-11-26","cited_by_count":2,"area":null}],"next_cursor":"100"}