{"total":330,"rows":[{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469,"area":"safety"},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2102.00436","title":"Admix: Enhancing the Transferability of Adversarial Attacks","created":"2021-01-31","cited_by_count":156,"area":null},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134,"area":"diffusion"},{"id":"2206.10550","title":"(Certified!!) Adversarial Robustness for Free!","created":"2022-06-21","cited_by_count":132,"area":"diffusion"},{"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":"2102.08452","title":"Globally-Robust Neural Networks","created":"2021-02-16","cited_by_count":108,"area":null},{"id":"2103.03638","title":"PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations","created":"2021-03-05","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":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"area":"alignment"},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71,"area":null},{"id":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67,"area":null},{"id":"2108.09135","title":"PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier","created":"2021-08-20","cited_by_count":65,"area":null},{"id":"2111.01395","title":"Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds","created":"2021-11-02","cited_by_count":65,"area":null},{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60,"area":null},{"id":"2303.03169","title":"A Unified Algebraic Perspective on Lipschitz Neural Networks","created":"2023-03-06","cited_by_count":60,"area":null},{"id":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59,"area":null},{"id":"2103.10609","title":"Boosting Adversarial Transferability through Enhanced Momentum","created":"2021-03-19","cited_by_count":54,"area":null},{"id":"2210.04871","title":"Certified Training: Small Boxes are All You Need","created":"2022-10-10","cited_by_count":52,"area":null},{"id":"2210.01787","title":"Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective","created":"2022-10-04","cited_by_count":51,"area":null},{"id":"2103.03046","title":"PointGuard: Provably Robust 3D Point Cloud Classification","created":"2021-03-04","cited_by_count":49,"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":"2104.11470","title":"Random Noise Defense Against Query-Based Black-Box Attacks","created":"2021-04-23","cited_by_count":47,"area":null},{"id":"2106.06946","title":"Boosting Randomized Smoothing with Variance Reduced Classifiers","created":"2021-06-13","cited_by_count":47,"area":null},{"id":"2108.04062","title":"Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100","created":"2021-08-05","cited_by_count":47,"area":null},{"id":"2103.17268","title":"Fast Certified Robust Training with Short Warmup","created":"2021-03-31","cited_by_count":46,"area":null},{"id":"2110.07719","title":"Certified Patch Robustness via Smoothed Vision Transformers","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"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":"2102.05363","title":"Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons","created":"2021-02-10","cited_by_count":40,"area":null},{"id":"2106.11420","title":"Policy Smoothing for Provably Robust Reinforcement Learning","created":"2021-06-21","cited_by_count":40,"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":"2103.10834","title":"Improved, Deterministic Smoothing for L_1 Certified Robustness","created":"2021-03-17","cited_by_count":39,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","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":"2107.00228","title":"Scalable Certified Segmentation via Randomized Smoothing","created":"2021-07-01","cited_by_count":35,"area":null},{"id":"2211.00322","title":"DensePure: Understanding Diffusion Models towards Adversarial Robustness","created":"2022-11-01","cited_by_count":33,"area":"diffusion"},{"id":"2403.12404","title":"Understanding and Improving Training-free Loss-based Diffusion Guidance","created":"2024-03-19","cited_by_count":32,"area":"diffusion"},{"id":"2102.02956","title":"DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2211.12681","title":"Benchmarking Adversarially Robust Quantum Machine Learning at Scale","created":"2022-11-23","cited_by_count":29,"area":null},{"id":"2306.12688","title":"Towards quantum enhanced adversarial robustness in machine learning","created":"2023-06-22","cited_by_count":28,"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":"2404.19651","title":"Provably Robust Conformal Prediction with Improved Efficiency","created":"2024-04-30","cited_by_count":27,"area":null},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2307.16360","title":"Probabilistically robust conformal prediction","created":"2023-07-31","cited_by_count":25,"area":null},{"id":"2102.02145","title":"Adversarially Robust Learning with Unknown Perturbation Sets","created":"2021-02-03","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":"2110.05365","title":"Intriguing Properties of Input-dependent Randomized Smoothing","created":"2021-10-11","cited_by_count":24,"area":null},{"id":"2110.06850","title":"Boosting the Certified Robustness of L-infinity Distance Nets","created":"2021-10-13","cited_by_count":24,"area":null},{"id":"2402.02316","title":"Your Diffusion Model is Secretly a Certifiably Robust Classifier","created":"2024-02-04","cited_by_count":24,"area":"diffusion"},{"id":"2107.04570","title":"ANCER: Anisotropic Certification via Sample-wise Volume Maximization","created":"2021-07-09","cited_by_count":23,"area":null},{"id":"2305.13991","title":"Expressive Losses for Verified Robustness via Convex Combinations","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2202.01811","title":"ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking","created":"2022-02-03","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":"2206.14772","title":"IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound","created":"2022-06-29","cited_by_count":21,"area":null},{"id":"2210.06983","title":"Denoising Masked AutoEncoders Help Robust Classification","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2310.00116","title":"Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization","created":"2023-09-29","cited_by_count":21,"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":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2308.14333","title":"DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing","created":"2023-08-28","cited_by_count":20,"area":"diffusion"},{"id":"2109.10696","title":"CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2205.12134","title":"Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks","created":"2022-05-24","cited_by_count":19,"area":null},{"id":"2102.09701","title":"Center Smoothing: Certified Robustness for Networks with Structured Outputs","created":"2021-02-19","cited_by_count":18,"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":"2405.03316","title":"Provably Unlearnable Data Examples","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2107.00996","title":"DeformRS: Certifying Input Deformations with Randomized Smoothing","created":"2021-07-02","cited_by_count":17,"area":null},{"id":"2112.00659","title":"Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines","created":"2021-12-01","cited_by_count":17,"area":null},{"id":"2302.01757","title":"RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion","created":"2023-01-31","cited_by_count":17,"area":null},{"id":"2103.16652","title":"Robustness Certification for Point Cloud Models","created":"2021-03-30","cited_by_count":16,"area":null},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16,"area":null},{"id":"2403.10144","title":"NLP Verification: Towards a General Methodology for Certifying Robustness","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2407.09165","title":"Robust Yet Efficient Conformal Prediction Sets","created":"2024-07-12","cited_by_count":16,"area":null},{"id":"2103.03438","title":"Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2107.11252","title":"Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2202.11910","title":"Robust Probabilistic Time Series Forecasting","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2206.11225","title":"RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval","created":"2022-06-17","cited_by_count":15,"area":null},{"id":"2207.11378","title":"Do Perceptually Aligned Gradients Imply Adversarial Robustness?","created":"2022-07-22","cited_by_count":15,"area":null},{"id":"2210.06077","title":"Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2310.18274","title":"LipSim: A Provably Robust Perceptual Similarity Metric","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2404.09586","title":"Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing","created":"2024-04-15","cited_by_count":15,"area":null},{"id":"2102.07559","title":"Certifiably Robust Variational Autoencoders","created":"2021-02-15","cited_by_count":14,"area":null},{"id":"2105.11363","title":"Learning Security Classifiers with Verified Global Robustness Properties","created":"2021-05-24","cited_by_count":14,"area":null},{"id":"2207.03574","title":"Demystifying the Adversarial Robustness of Random Transformation Defenses","created":"2022-06-18","cited_by_count":14,"area":null},{"id":"2102.11069","title":"A PAC-Bayes Analysis of Adversarial Robustness","created":"2021-02-19","cited_by_count":13,"area":null},{"id":"2201.01102","title":"Towards Transferable Unrestricted Adversarial Examples with Minimum Changes","created":"2022-01-04","cited_by_count":13,"area":null},{"id":"2203.17209","title":"Adversarial Examples in Random Neural Networks with General Activations","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2211.01258","title":"Instance-Dependent Generalization Bounds via Optimal Transport","created":"2022-11-02","cited_by_count":13,"area":null},{"id":"2301.12549","title":"Unlocking Deterministic Robustness Certification on ImageNet","created":"2023-01-29","cited_by_count":13,"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":"2505.17646","title":"Unveiling the Basin-Like Loss Landscape in Large Language Models","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2102.06700","title":"On the Paradox of Certified Training","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2204.00487","title":"Robust and Accurate -- Compositional Architectures for Randomized Smoothing","created":"2022-04-01","cited_by_count":12,"area":null},{"id":"2110.04337","title":"Adversarial Token Attacks on Vision Transformers","created":"2021-10-08","cited_by_count":11,"area":null},{"id":"2112.07324","title":"On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training","created":"2021-12-14","cited_by_count":11,"area":null},{"id":"2112.12084","title":"Input-Specific Robustness Certification for Randomized Smoothing","created":"2021-12-21","cited_by_count":11,"area":null}],"next_cursor":"100"}