Volgen
Gagandeep Singh
Gagandeep Singh
Assistant Professor, Department of Computer Science, UIUC
Geverifieerd e-mailadres voor illinois.edu - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
An abstract domain for certifying neural networks
G Singh, T Gehr, M Püschel, M Vechev
Proceedings of the ACM on Programming Languages 3 (POPL), 1-30, 2019
8612019
Fast and effective robustness certification
G Singh, T Gehr, M Mirman, M Püschel, M Vechev
Advances in neural information processing systems 31, 2018
6412018
Boosting robustness certification of neural networks
G Singh, T Gehr, M Püschel, M Vechev
International conference on learning representations, 2019
2542019
Beyond the single neuron convex barrier for neural network certification
G Singh, R Ganvir, M Püschel, M Vechev
Advances in Neural Information Processing Systems 32, 15098-15109, 2019
2372019
PRIMA: general and precise neural network certification via scalable convex hull approximations.
MN Müller, G Makarchuk, G Singh, M Püschel, MT Vechev
Proc. ACM Program. Lang. 6 (POPL), 1-33, 2022
151*2022
Certifying geometric robustness of neural networks
M Balunovic, M Baader, G Singh, T Gehr, M Vechev
Advances in Neural Information Processing Systems 32, 2019
1462019
Fast polyhedra abstract domain
G Singh, M Püschel, M Vechev
Proceedings of the 44th ACM SIGPLAN Symposium on Principles of Programming …, 2017
1422017
Scaling polyhedral neural network verification on GPUs
C Müller, F Serre, G Singh, M Püschel, M Vechev
Proceedings of Machine Learning and Systems 3, 733-746, 2021
81*2021
Making Numerical Program Analysis Fast
G Singh, M Püschel, M Vechev
Programming Language Design and Implementation (PLDI) 50 (6), 303-313, 2015
632015
Scalable Polyhedral Verification of Recurrent Neural Networks
W Ryou, J Chen, M Balunovic, G Singh, A Dan, M Vechev
International Conference on Computer Aided Verification, 225-248, 2021
54*2021
A practical construction for decomposing numerical abstract domains
G Singh, M Püschel, M Vechev
Proceedings of the ACM on Programming Languages 2 (POPL), 1-28, 2017
482017
Improving llm code generation with grammar augmentation
S Ugare, T Suresh, H Kang, S Misailovic, G Singh
arXiv preprint arXiv:2403.01632, 2024
41*2024
Fast numerical program analysis with reinforcement learning
G Singh, M Püschel, M Vechev
Computer Aided Verification: 30th International Conference, CAV 2018, Held …, 2018
392018
FIRE: enabling reciprocity for FDD MIMO systems
Z Liu, G Singh, C Xu, D Vasisht
Proceedings of the 27th Annual International Conference on Mobile Computing …, 2021
352021
Robustness certification for point cloud models
T Lorenz, A Ruoss, M Balunović, G Singh, M Vechev
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
332021
Learning fast and precise numerical analysis
J He, G Singh, M Püschel, M Vechev
Proceedings of the 41st ACM SIGPLAN Conference on Programming Language …, 2020
332020
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
R Dang-Nhu, G Singh, P Bielik, M Vechev
International Conference on Machine Learning, 2020
302020
A Provable Defense for Deep Residual Networks
M Mirman, G Singh, M Vechev
arXiv preprint arXiv:1903.12519, 2019
252019
A dual number abstraction for static analysis of Clarke Jacobians
J Laurel, R Yang, G Singh, S Misailovic
Proceedings of the ACM on Programming Languages 6 (POPL), 1-30, 2022
212022
Provable Defense Against Geometric Transformations
R Yang, J Laurel, S Misailovic, G Singh
International Conference on Learning Representations (ICLR 2023), 2023
19*2023
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20