{"total":179,"rows":[{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2103.06624","title":"Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification","created":"2021-03-11","cited_by_count":228,"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":"2208.05740","title":"General Cutting Planes for Bound-Propagation-Based Neural Network Verification","created":"2022-08-11","cited_by_count":103,"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":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","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":"2106.12723","title":"Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations","created":"2021-06-24","cited_by_count":53,"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":"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":"2104.06718","title":"Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition","created":"2021-04-14","cited_by_count":44,"area":null},{"id":"2101.09617","title":"A Comprehensive Evaluation Framework for Deep Model Robustness","created":"2021-01-24","cited_by_count":42,"area":null},{"id":"2206.12227","title":"Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective","created":"2022-06-24","cited_by_count":42,"area":null},{"id":"2106.11420","title":"Policy Smoothing for Provably Robust Reinforcement Learning","created":"2021-06-21","cited_by_count":40,"area":null},{"id":"2102.04373","title":"Partition-based formulations for mixed-integer optimization of trained ReLU neural networks","created":"2021-02-08","cited_by_count":39,"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":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","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":"2202.02414","title":"OMLT: Optimization & Machine Learning Toolkit","created":"2022-02-04","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":"2112.01694","title":"On the Existence of the Adversarial Bayes Classifier (Extended Version)","created":"2021-12-03","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":"2110.06850","title":"Boosting the Certified Robustness of L-infinity Distance Nets","created":"2021-10-13","cited_by_count":24,"area":null},{"id":"2203.11201","title":"Efficient Neural Network Analysis with Sum-of-Infeasibilities","created":"2022-03-19","cited_by_count":24,"area":null},{"id":"2207.02715","title":"Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopes","created":"2022-07-06","cited_by_count":24,"area":null},{"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":"2110.01110","title":"Safe Control with Neural Network Dynamic Models","created":"2021-10-03","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":"2310.00116","title":"Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization","created":"2023-09-29","cited_by_count":21,"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":"2203.03153","title":"Scalable Verification of GNN-based Job Schedulers","created":"2022-03-07","cited_by_count":19,"area":null},{"id":"2303.01713","title":"Convex Bounds on the Softmax Function with Applications to Robustness Verification","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2102.09479","title":"Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications","created":"2021-02-18","cited_by_count":18,"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":"2209.14076","title":"Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems","created":"2022-09-28","cited_by_count":18,"area":null},{"id":"2406.11779","title":"Compact Proofs of Model Performance via Mechanistic Interpretability","created":"2024-06-17","cited_by_count":18,"area":"mechinterp"},{"id":"2102.12002","title":"Adversarial Robustness with Non-uniform Perturbations","created":"2021-02-24","cited_by_count":17,"area":null},{"id":"2107.00996","title":"DeformRS: Certifying Input Deformations with Randomized Smoothing","created":"2021-07-02","cited_by_count":17,"area":null},{"id":"2109.06795","title":"ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation","created":"2021-09-14","cited_by_count":17,"area":null},{"id":"2302.02300","title":"Run-Off Election: Improved Provable Defense against Data Poisoning Attacks","created":"2023-02-05","cited_by_count":17,"area":"safety"},{"id":"2103.16652","title":"Robustness Certification for Point Cloud Models","created":"2021-03-30","cited_by_count":16,"area":null},{"id":"2206.03669","title":"Toward Certified Robustness Against Real-World Distribution Shifts","created":"2022-06-08","cited_by_count":16,"area":null},{"id":"2306.09844","title":"Wasserstein distributional robustness of neural networks","created":"2023-06-16","cited_by_count":16,"area":null},{"id":"2202.11910","title":"Robust Probabilistic Time Series Forecasting","created":"2022-02-24","cited_by_count":15,"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":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2512.01295","title":"Systems Security Foundations for Agentic Computing","created":"2025-12-01","cited_by_count":13,"area":"agents"},{"id":"2102.06700","title":"On the Paradox of Certified Training","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2203.03034","title":"A Unified View of SDP-based Neural Network Verification through Completely Positive Programming","created":"2022-03-06","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":"2506.06665","title":"SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming","created":"2025-06-07","cited_by_count":12,"area":null},{"id":"2103.12171","title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","created":"2021-03-22","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},{"id":"2205.14189","title":"Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2309.13794","title":"Projected Randomized Smoothing for Certified Adversarial Robustness","created":"2023-09-25","cited_by_count":11,"area":null},{"id":"2312.12679","title":"Towards Efficient Verification of Quantized Neural Networks","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2101.05844","title":"Scaling the Convex Barrier with Sparse Dual Algorithms","created":"2021-01-14","cited_by_count":10,"area":null},{"id":"2109.00542","title":"Shared Certificates for Neural Network Verification","created":"2021-09-01","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":"2206.07839","title":"Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2207.02152","title":"UniCR: Universally Approximated Certified Robustness via Randomized Smoothing","created":"2022-07-05","cited_by_count":10,"area":null},{"id":"2209.05055","title":"CARE: Certifiably Robust Learning with Reasoning via Variational Inference","created":"2022-09-12","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":"2204.08319","title":"Backward Reachability Analysis for Neural Feedback Loops","created":"2022-04-14","cited_by_count":9,"area":null},{"id":"2211.08453","title":"Improved techniques for deterministic l2 robustness","created":"2022-11-15","cited_by_count":9,"area":null},{"id":"2512.11087","title":"Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2106.09117","title":"DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting","created":"2021-06-16","cited_by_count":8,"area":null},{"id":"2110.15764","title":"{\\epsilon}-weakened Robustness of Deep Neural Networks","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2302.01961","title":"Asymmetric Certified Robustness via Feature-Convex Neural Networks","created":"2023-02-03","cited_by_count":8,"area":null},{"id":"2311.04015","title":"Expressivity of ReLU-Networks under Convex Relaxations","created":"2023-11-07","cited_by_count":8,"area":null},{"id":"2104.00322","title":"Domain Invariant Adversarial Learning","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2205.03824","title":"A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2211.01498","title":"On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2305.17342","title":"Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL","created":"2023-05-27","cited_by_count":7,"area":null},{"id":"2306.13614","title":"Adversarial Robustness Certification for Bayesian Neural Networks","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2408.02691","title":"Symmetric Graph Contrastive Learning against Noisy Views for Recommendation","created":"2024-08-03","cited_by_count":7,"area":null},{"id":"2408.13140","title":"Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2106.14432","title":"Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2107.06534","title":"Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimization","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2210.07918","title":"A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2503.08801","title":"Enhanced Estimation Techniques for Certified Radii in Randomized Smoothing","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2201.12440","title":"Certifying Model Accuracy under Distribution Shifts","created":"2022-01-28","cited_by_count":5,"area":null},{"id":"2203.08961","title":"On the Convergence of Certified Robust Training with Interval Bound Propagation","created":"2022-03-16","cited_by_count":5,"area":null},{"id":"2205.06992","title":"Verifying Neural Networks Against Backdoor Attacks","created":"2022-05-14","cited_by_count":5,"area":null},{"id":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2210.08069","title":"Zonotope Domains for Lagrangian Neural Network Verification","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2212.01544","title":"Probabilistic Verification of ReLU Neural Networks via Characteristic Functions","created":"2022-12-03","cited_by_count":5,"area":null},{"id":"2303.03042","title":"Convolutional Neural Networks as 2-D systems","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2304.02693","title":"A Certified Radius-Guided Attack Framework to Image Segmentation Models","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2310.02480","title":"Splitting the Difference on Adversarial Training","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2401.11188","title":"Fast and Exact Enumeration of Deep Networks Partitions Regions","created":"2024-01-20","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}],"next_cursor":"100"}