certified robustness

Certified Robustness to Word Substitution Attack with Differential Privacy NAACL 2021 Certify or Predict: Boosting Certified Robustness with Compositional Architectures ICLR 2021 Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions AISTATS 2021 DSRNA: Differentiable Search of Robust Neural Architectures CVPR 2021 Efficient Certified Defenses Against Patch Attacks on Image Classifiers ICLR 2021 Fast Certified Robust Training with Short Warmup NeurIPS 2021 Globally-Robust Neural Networks ICML 2021 How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021 Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021 Integer-Arithmetic-Only Certified Robustness for Quantized Neural Networks ICCV 2021 Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks AAAI 2021 PointGuard: Provably Robust 3D Point Cloud Classification CVPR 2021 Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness EMNLP 2021 Provably robust classification of adversarial examples with detection ICLR 2021 Relaxing Local Robustness NeurIPS 2021 Skew Orthogonal Convolutions ICML 2021 SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness NeurIPS 2021 Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021 Towards Evaluating and Training Verifiably Robust Neural Networks CVPR 2021 Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds NeurIPS 2021 Adversarial robustness via robust low rank representations NeurIPS 2020 Adversarial Training and Provable Defenses: Bridging the Gap ICLR 2020 Assessing Robustness of Text Classification through Maximal Safe Radius Computation EMNLP 2020 Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond NeurIPS 2020 Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework NeurIPS 2020