Safety Verification

Paper Collection for Robustness and Safety Verification

ExactReach: Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations, 2017
MaxSens: Output Reachable Set Estimation and Verification for Multi-layer Neural Networks, 2018
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation, 2018
DeepZ: Fast and Effective Robustness Certification, 2018

FastLin -> CROWN: Efficient Neural Network Robustness Certification with General Activation Functions, 2018
FastLip -> RecurJac: RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications, 2019
ReluVal: Formal Security Analysis of Neural Networks using Symbolic Intervals, 2018
DLV: Safety Verification of Deep Neural Networks, 2017

DLV: An Approach to Reachability Analysis for Feed-Forward Relu Neural Networks, 2017
MIPVerify: Evaluating Robustness of Neural Networks with Mixed Integer Programming, 2017
ILP: Measuring Neural Net Robustness with Constraints, 2016
Duality: A Dual Approach to Scalable Verification of Deep Networks, 2018
ConvDual: Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope, 2018
Certify: Certified Defenses against Adversarial Examples, 2018
DeepGO: Reachability Analysis of Deep Neural Networks with Provable Guarantees, 2018
Decomposition: Lagrangian Decomposition for Neural Network Verification, 2020

Sherlock: Output Range Analysis for Deep Neural Networks, 2017
BaB: A Unified View of Piecewise Linear Neural Network Verification, 2018
Planet: Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks, 2017
Reluplex: Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks, 2017
GNN_branching: Neural Network Branching for Neural Network Verification, 2019

Certified robustness to adversarial examples with differential privacy, 2018
Certified Adversarial Robustness with Additive Noise, 2019
Certified Adversarial Robustness via Randomized Smoothing, 2019
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers, 2019
Rethinking Randomized Smoothing for Adversarial Robustness, 2020
Extensions and limitations of randomized smoothing for robustness guarantees, 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness, 2020
Randomized Smoothing of All Shapes and Sizes, 2020
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More, 2020
Scalable Differential Privacy with Certified Robustness in Adversarial Learning, 2020
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing, 2020

Automated Verification of Neural Networks: Advances, Challenges and Perspectives, 2018
Algorithms for verifying deep neural networks, 2019
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability, 2020

method-compare

Paper List