Gagandeep Singh

Affiliations:
  • University of Illinois Urbana-Champaign, IL, USA
  • ETH Zurich, Switzerland (PhD 2020)


According to our database1, Gagandeep Singh authored at least 23 papers between 2015 and 2022.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2022
Proof transfer for fast certification of multiple approximate neural networks.
Proc. ACM Program. Lang., 2022

PRIMA: general and precise neural network certification via scalable convex hull approximations.
Proc. ACM Program. Lang., 2022

A dual number abstraction for static analysis of Clarke Jacobians.
Proc. ACM Program. Lang., 2022

2021
Shared Certificates for Neural Network Verification.
CoRR, 2021

Precise Multi-Neuron Abstractions for Neural Network Certification.
CoRR, 2021

Scaling Polyhedral Neural Network Verification on GPUs.
Proceedings of Machine Learning and Systems 2021, 2021

Robustness Certification for Point Cloud Models.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Scalable Polyhedral Verification of Recurrent Neural Networks.
Proceedings of the Computer Aided Verification - 33rd International Conference, 2021

2020
Scalable Inference of Symbolic Adversarial Examples.
CoRR, 2020

Neural Network Robustness Verification on GPUs.
CoRR, 2020

Fast and Effective Robustness Certification for Recurrent Neural Networks.
CoRR, 2020

Learning fast and precise numerical analysis.
Proceedings of the 41st ACM SIGPLAN International Conference on Programming Language Design and Implementation, 2020

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models.
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
An abstract domain for certifying neural networks.
Proc. ACM Program. Lang., 2019

A Provable Defense for Deep Residual Networks.
CoRR, 2019

Beyond the Single Neuron Convex Barrier for Neural Network Certification.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Certifying Geometric Robustness of Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Boosting Robustness Certification of Neural Networks.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
A practical construction for decomposing numerical abstract domains.
Proc. ACM Program. Lang., 2018

Fast and Effective Robustness Certification.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Fast Numerical Program Analysis with Reinforcement Learning.
Proceedings of the Computer Aided Verification - 30th International Conference, 2018

2017
Fast polyhedra abstract domain.
Proceedings of the 44th ACM SIGPLAN Symposium on Principles of Programming Languages, 2017

2015
Making numerical program analysis fast.
Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2015


  Loading...