About me

I am a PhD student in the Secure, Reliable, and Intelligent Systems Lab supervised by Prof. Martin Vechev and Prof. Markus Püschel since Nov 2014. I was born in Raebareli, India. I am broadly interested in balancing the precision/performance tradeoff of numerical problems. Examples include numerical domains used in abstract interpretation and robustness analysis of neural networks. I will be starting as an assistant professor of CS at UIUC from August 2021.

Publications

2022

Shared Certificates for Neural Network Verification
Marc Fischer*, Christian Sprecher*, Dimitar I. Dimitrov, Gagandeep Singh, Martin Vechev
CAV 2022 * Equal contribution
Provably Robust Adversarial Examples
Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev
ICLR 2022
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations
Mark Niklas Müller*, Gleb Makarchuk*, Gagandeep Singh, Markus Püschel, Martin Vechev
POPL 2022 * Equal contribution

2021

Robustness Certification for Point Cloud Models
Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev
ICCV 2021
Scalable Polyhedral Verification of Recurrent Neural Networks
Wonryong Ryou, Jiayu Chen, Mislav Balunović, Gagandeep Singh, Andrei Dan, Martin Vechev
CAV 2021
Scaling Polyhedral Neural Network Verification on GPUs
Christoph Müller*, François Serre*, Gagandeep Singh, Markus Püschel, Martin Vechev
MLSys 2021 * Equal contribution

2020

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin Vechev
ICML 2020
Learning Fast and Precise Numerical Analysis
Jingxuan He, Gagandeep Singh, Markus Püschel, Martin Vechev
PLDI 2020

2019

Beyond the Single Neuron Convex Barrier for Neural Network Certification
Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin Vechev
NeurIPS 2019
Certifying Geometric Robustness of Neural Networks
Mislav Balunović, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev
NeurIPS 2019
Boosting Robustness Certification of Neural Networks
Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev
ICLR 2019
A Provable Defense for Deep Residual Networks
Matthew Mirman, Gagandeep Singh, Martin Vechev
ArXiv 2019
An Abstract Domain for Certifying Neural Networks
Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev
ACM POPL 2019

2018

Fast and Effective Robustness Certification
Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
NIPS 2018
Fast Numerical Program Analysis with Reinforcement Learning
Gagandeep Singh, Markus Püschel, Martin Vechev
CAV 2018
A Practical Construction for Decomposing Numerical Abstract Domains
Gagandeep Singh, Markus Püschel, Martin Vechev
ACM POPL 2018

2017

Fast Polyhedra Abstract Domain
Gagandeep Singh, Markus Püschel, Martin Vechev
ACM POPL 2017

2015

Making Numerical Program Analysis Fast
Gagandeep Singh, Markus Püschel, Martin Vechev
ACM PLDI 2015

Education

  • ETH Zurich, Sep 2012 - April 2014
    M.Sc. in Computer Science
  • IIT Patna, Aug 2008 - May 2012
    B.Tech in Computer Science and Engineering

Internships

  • University of Houston, USA, 2010
    Developed software for accurate eye center detection
  • University of New South Wales, Australia, 2011
    Worked on Predictive Model for forecasting conflicts between nations

Teaching

  • Algorithmen und Datenstrukturen
    Autumn 2017
  • How to Write Fast Numerical Code
    Spring 2017
  • How to Write Fast Numerical Code
    Spring 2016
  • How to Write Fast Numerical Code
    Spring 2015

Awards and Honors

  • 2014: ETH Medal for Best Master Thesis
  • 2012: ETH Excellence Scholarship
  • 2012: President of India Gold Medal, IIT Patna
  • 2007: Selected in SCRA (10 out of >1,000,000)