conftrace_

robustness certification

47 papers

Explore in graph

Co-occurring keywords

adversarial robustness (1341) randomized smoothing (87) neural network (6616) certified robustness (116) semidefinite programming (147) neural network robustness (92) neural network verification (106) adversarial attack (1621) adversarial example (564) certified defense (34)

Papers

On Collective Robustness of Bagging Against Data Poisoning ICML 2022
Double Sampling Randomized Smoothing ICML 2022
Input-Specific Robustness Certification for Randomized Smoothing AAAI 2022
Robustness Certification of Visual Perception Models via Camera Motion Smoothing CORL 2022
Invariance-Aware Randomized Smoothing Certificates NIPS 2022
Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations AAAI 2022
GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022
Certifying Robustness to Programmable Data Bias in Decision Trees NIPS 2021
Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021
Robustness Certification for Point Cloud Models ICCV 2021
Efficient Certification of Spatial Robustness AAAI 2021
Adversarial Robustness with Non-uniform Perturbations NIPS 2021
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks ICML 2021
Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification NIPS 2021
Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness AAAI 2020
Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms NIPS 2020
Semialgebraic Optimization for Lipschitz Constants of ReLU Networks NIPS 2020
Provably Robust Metric Learning NIPS 2020
On Certifying Non-Uniform Bounds against Adversarial Attacks ICML 2019
Defending against Whitebox Adversarial Attacks via Randomized Discretization AISTATS 2019
Semidefinite relaxations for certifying robustness to adversarial examples NIPS 2018