{"total":416,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316,"area":"mllm"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288,"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":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234,"area":null},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210,"area":null},{"id":"2302.04638","title":"Better Diffusion Models Further Improve Adversarial Training","created":"2023-02-09","cited_by_count":208,"area":"diffusion"},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207,"area":null},{"id":"2103.01946","title":"Fixing Data Augmentation to Improve Adversarial Robustness","created":"2021-03-02","cited_by_count":204,"area":null},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134,"area":"diffusion"},{"id":"2102.06203","title":"Proof Artifact Co-training for Theorem Proving with Language Models","created":"2021-02-11","cited_by_count":132,"area":"offlinerl"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113,"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":"2207.09640","title":"Test-Time Adaptation via Conjugate Pseudo-labels","created":"2022-07-20","cited_by_count":98,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2205.14969","title":"Guided Diffusion Model for Adversarial Purification","created":"2022-05-30","cited_by_count":92,"area":"diffusion"},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85,"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":"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":"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":"2112.12376","title":"Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization","created":"2021-12-23","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":"2305.10862","title":"How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses","created":"2023-05-18","cited_by_count":66,"area":null},{"id":"2202.13711","title":"Evaluating the Adversarial Robustness of Adaptive Test-time Defenses","created":"2022-02-28","cited_by_count":64,"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":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60,"area":null},{"id":"2106.10891","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","created":"2021-06-21","cited_by_count":59,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2106.07904","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","created":"2021-06-15","cited_by_count":57,"area":null},{"id":"2106.04928","title":"Reliable Adversarial Distillation with Unreliable Teachers","created":"2021-06-09","cited_by_count":56,"area":"distill"},{"id":"2106.01606","title":"Exploring Memorization in Adversarial Training","created":"2021-06-03","cited_by_count":55,"area":null},{"id":"2208.11296","title":"Semi-Supervised and Unsupervised Deep Visual Learning: A Survey","created":"2022-08-24","cited_by_count":52,"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":"2206.08675","title":"Understanding Robust Overfitting of Adversarial Training and Beyond","created":"2022-06-17","cited_by_count":51,"area":null},{"id":"2102.12827","title":"Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints","created":"2021-02-25","cited_by_count":50,"area":null},{"id":"2104.02703","title":"Adversarial Robustness under Long-Tailed Distribution","created":"2021-04-06","cited_by_count":50,"area":null},{"id":"2102.10496","title":"Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits","created":"2021-02-21","cited_by_count":49,"area":"safety"},{"id":"2107.11630","title":"Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them","created":"2021-07-24","cited_by_count":48,"area":null},{"id":"2104.09658","title":"Calibration and Consistency of Adversarial Surrogate Losses","created":"2021-04-19","cited_by_count":47,"area":null},{"id":"2108.08993","title":"Distributionally Robust Learning","created":"2021-08-20","cited_by_count":44,"area":null},{"id":"2203.05154","title":"Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack","created":"2022-03-10","cited_by_count":44,"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":"2301.09879","title":"Data Augmentation Alone Can Improve Adversarial Training","created":"2023-01-24","cited_by_count":43,"area":null},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","cited_by_count":43,"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":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2106.08226","title":"Consistency Regularization for Cross-Lingual Fine-Tuning","created":"2021-06-15","cited_by_count":41,"area":null},{"id":"2107.10873","title":"On the Certified Robustness for Ensemble Models and Beyond","created":"2021-07-22","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":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39,"area":null},{"id":"2106.06196","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","created":"2021-06-11","cited_by_count":37,"area":null},{"id":"2106.10189","title":"Adversarial Training Helps Transfer Learning via Better Representations","created":"2021-06-18","cited_by_count":36,"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":"2210.06284","title":"Visual Prompting for Adversarial Robustness","created":"2022-10-12","cited_by_count":34,"area":null},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2105.10304","title":"Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks","created":"2021-05-21","cited_by_count":33,"area":null},{"id":"2105.14240","title":"Analysis and Applications of Class-wise Robustness in Adversarial Training","created":"2021-05-29","cited_by_count":33,"area":null},{"id":"2210.11620","title":"LOT: Layer-wise Orthogonal Training on Improving $\\ell_2$ Certified Robustness","created":"2022-10-20","cited_by_count":33,"area":null},{"id":"2106.04938","title":"Attacking Adversarial Attacks as A Defense","created":"2021-06-09","cited_by_count":32,"area":null},{"id":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2210.00960","title":"Stability Analysis and Generalization Bounds of Adversarial Training","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2102.10454","title":"On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning","created":"2021-02-20","cited_by_count":29,"area":null},{"id":"2110.04471","title":"Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning","created":"2021-10-09","cited_by_count":29,"area":null},{"id":"2111.09961","title":"A Review of Adversarial Attack and Defense for Classification Methods","created":"2021-11-18","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":"2212.11005","title":"Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective","created":"2022-12-21","cited_by_count":28,"area":null},{"id":"2303.10653","title":"Randomized Adversarial Training via Taylor Expansion","created":"2023-03-19","cited_by_count":28,"area":null},{"id":"2103.14347","title":"Combating Adversaries with Anti-Adversaries","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2107.14110","title":"Enhancing Adversarial Robustness via Test-time Transformation Ensembling","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2302.04025","title":"WAT: Improve the Worst-class Robustness in Adversarial Training","created":"2023-02-08","cited_by_count":27,"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":"2205.14826","title":"Robust Weight Perturbation for Adversarial Training","created":"2022-05-30","cited_by_count":25,"area":null},{"id":"2210.05938","title":"Robust Models are less Over-Confident","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2104.09284","title":"LAFEAT: Piercing Through Adversarial Defenses with Latent Features","created":"2021-04-19","cited_by_count":24,"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":"2212.06515","title":"AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images","created":"2022-12-13","cited_by_count":24,"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":"2106.09947","title":"Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples","created":"2021-06-18","cited_by_count":23,"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":"2209.14105","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","created":"2022-09-28","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":"2102.06905","title":"Mixed Nash Equilibria in the Adversarial Examples Game","created":"2021-02-13","cited_by_count":22,"area":null},{"id":"2102.11860","title":"Automated Discovery of Adaptive Attacks on Adversarial Defenses","created":"2021-02-23","cited_by_count":22,"area":null},{"id":"2110.05626","title":"Parameterizing Activation Functions for Adversarial Robustness","created":"2021-10-11","cited_by_count":22,"area":null},{"id":"2206.07912","title":"Double Sampling Randomized Smoothing","created":"2022-06-16","cited_by_count":22,"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":"2210.06983","title":"Denoising Masked AutoEncoders Help Robust Classification","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2212.09254","title":"TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization","created":"2022-12-19","cited_by_count":21,"area":null},{"id":"2105.08714","title":"Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks","created":"2021-05-18","cited_by_count":20,"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}],"next_cursor":"100"}