{"total":89,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"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":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89,"area":null},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79,"area":"distill"},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79,"area":null},{"id":"2303.01870","title":"Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models","created":"2023-03-03","cited_by_count":79,"area":null},{"id":"2209.07399","title":"A Light Recipe to Train Robust Vision Transformers","created":"2022-09-15","cited_by_count":64,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"id":"2104.02703","title":"Adversarial Robustness under Long-Tailed Distribution","created":"2021-04-06","cited_by_count":50,"area":null},{"id":"2308.16258","title":"Robust Principles: Architectural Design Principles for Adversarially Robust CNNs","created":"2023-08-30","cited_by_count":46,"area":null},{"id":"2210.15318","title":"Efficient and Effective Augmentation Strategy for Adversarial Training","created":"2022-10-27","cited_by_count":43,"area":null},{"id":"2110.14188","title":"RoMA: Robust Model Adaptation for Offline Model-based Optimization","created":"2021-10-27","cited_by_count":39,"area":null},{"id":"2202.13437","title":"A Unified Wasserstein Distributional Robustness Framework for Adversarial Training","created":"2022-02-27","cited_by_count":36,"area":null},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34,"area":null},{"id":"2401.04727","title":"Revisiting Adversarial Training at Scale","created":"2024-01-09","cited_by_count":33,"area":null},{"id":"2102.07861","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","created":"2021-02-15","cited_by_count":29,"area":null},{"id":"2212.11005","title":"Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective","created":"2022-12-21","cited_by_count":28,"area":null},{"id":"2108.09093","title":"Towards Understanding the Generative Capability of Adversarially Robust Classifiers","created":"2021-08-20","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25,"area":null},{"id":"2108.11168","title":"Adversarially Robust One-class Novelty Detection","created":"2021-08-25","cited_by_count":24,"area":null},{"id":"2209.14105","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","created":"2022-09-28","cited_by_count":23,"area":null},{"id":"2110.05626","title":"Parameterizing Activation Functions for Adversarial Robustness","created":"2021-10-11","cited_by_count":22,"area":null},{"id":"2406.05927","title":"MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification","created":"2024-06-09","cited_by_count":21,"area":null},{"id":"2204.06213","title":"Defensive Patches for Robust Recognition in the Physical World","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2207.10899","title":"Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness","created":"2022-07-22","cited_by_count":20,"area":null},{"id":"2209.04121","title":"Fast Neural Kernel Embeddings for General Activations","created":"2022-09-09","cited_by_count":18,"area":null},{"id":"2208.00094","title":"Robust Trajectory Prediction against Adversarial Attacks","created":"2022-07-29","cited_by_count":17,"area":null},{"id":"2208.09801","title":"PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition","created":"2022-08-21","cited_by_count":16,"area":null},{"id":"2306.06712","title":"Neural Architecture Design and Robustness: A Dataset","created":"2023-06-11","cited_by_count":15,"area":null},{"id":"2107.04263","title":"Towards Robust General Medical Image Segmentation","created":"2021-07-09","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":"2108.05075","title":"Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks","created":"2021-08-11","cited_by_count":13,"area":null},{"id":"2202.08064","title":"Learning a Single Neuron for Non-monotonic Activation Functions","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2102.01886","title":"Learning Diverse-Structured Networks for Adversarial Robustness","created":"2021-02-03","cited_by_count":12,"area":null},{"id":"2306.08805","title":"Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification","created":"2023-06-15","cited_by_count":11,"area":null},{"id":"2307.13856","title":"On the unreasonable vulnerability of transformers for image restoration -- and an easy fix","created":"2023-07-25","cited_by_count":11,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2205.11156","title":"Squeeze Training for Adversarial Robustness","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2103.05354","title":"Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2107.06501","title":"AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning","created":"2021-07-14","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":"2101.10027","title":"Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning","created":"2021-01-25","cited_by_count":8,"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":"2301.03110","title":"RobArch: Designing Robust Architectures against Adversarial Attacks","created":"2023-01-08","cited_by_count":6,"area":null},{"id":"2304.12550","title":"Combining Adversaries with Anti-adversaries in Training","created":"2023-04-25","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":"2102.08868","title":"Bridging the Gap Between Adversarial Robustness and Optimization Bias","created":"2021-02-17","cited_by_count":5,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2311.10992","title":"Towards Robust and Accurate Visual Prompting","created":"2023-11-18","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":"2109.12456","title":"Auditing AI models for Verified Deployment under Semantic Specifications","created":"2021-09-25","cited_by_count":4,"area":null},{"id":"2209.06953","title":"On the interplay of adversarial robustness and architecture components: patches, convolution and attention","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2210.05118","title":"Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2509.22502","title":"InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios","created":"2025-09-26","cited_by_count":4,"area":"agents"},{"id":"2309.13245","title":"RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias","created":"2023-09-23","cited_by_count":3,"area":null},{"id":"2105.08269","title":"Sparta: Spatially Attentive and Adversarially Robust Activation","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2105.12427","title":"Deep Repulsive Prototypes for Adversarial Robustness","created":"2021-05-26","cited_by_count":2,"area":null},{"id":"2106.13394","title":"Countering Adversarial Examples: Combining Input Transformation and Noisy Training","created":"2021-06-25","cited_by_count":2,"area":null},{"id":"2202.06499","title":"Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations","created":"2022-02-14","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":"2304.00061","title":"To be Robust and to be Fair: Aligning Fairness with Robustness","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2310.04412","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2102.13170","title":"Understanding Robustness in Teacher-Student Setting: A New Perspective","created":"2021-02-25","cited_by_count":1,"area":"distill"},{"id":"2104.08382","title":"Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2106.10252","title":"Less is More: Feature Selection for Adversarial Robustness with Compressive Counter-Adversarial Attacks","created":"2021-06-18","cited_by_count":1,"area":null},{"id":"2107.04827","title":"Identifying Layers Susceptible to Adversarial Attacks","created":"2021-07-10","cited_by_count":1,"area":null},{"id":"2203.08959","title":"Robustness through Cognitive Dissociation Mitigation in Contrastive Adversarial Training","created":"2022-03-16","cited_by_count":1,"area":null},{"id":"2212.11760","title":"Aliasing is a Driver of Adversarial Attacks","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2303.07474","title":"Can Adversarial Examples Be Parsed to Reveal Victim Model Information?","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2302.02216","title":"A Minimax Approach Against Multi-Armed Adversarial Attacks Detection","created":"2023-02-04","cited_by_count":0,"area":null},{"id":"2304.03374","title":"Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2403.06013","title":"Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2403.19150","title":"Towards Understanding Dual BN In Hybrid Adversarial Training","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2404.19567","title":"Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2405.04074","title":"A simple theory for training response of deep neural networks","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2412.08282","title":"How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2503.16975","title":"EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2505.10037","title":"Optimal normalization in quantum-classical hybrid models for anti-cancer drug response prediction","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.04951","title":"Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.06556","title":"SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2511.05073","title":"Deep learning models are vulnerable, but adversarial examples are even more vulnerable","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2603.23860","title":"Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.25517","title":"NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.11558","title":"A Composite Activation Function for Learning Stable Binary Representations","created":"2026-05-12","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}],"next_cursor":null}