Posts by Collection

publications

Making Numerical Program Analysis Fast

Gagandeep Singh, Markus Püschel, Martin Vechev, PLDI 2015.

Fast Polyhedra Abstract Domain

Gagandeep Singh, Markus Püschel, Martin Vechev, POPL 2017.

A Practical Construction for Decomposing Numerical Abstract Domains

Gagandeep Singh, Markus Püschel, Martin Vechev, POPL 2018.

Fast Numerical Program Analysis with Reinforcement Learning

Gagandeep Singh, Markus Püschel, Martin Vechev, CAV 2018.

Fast and Effective Robustness Certification

Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev, NeurIPS 2018.

An Abstract Domain for Certifying Neural Networks

Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev, POPL 2019.

Boosting Robustness Certification of Neural Networks

Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev, ICLR 2019.

Certifying Geometric Robustness of Neural Networks

Mislav Balunovic, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev, NeurIPS 2019.

Beyond the Single Neuron Convex Barrier for Neural Network Certification

Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin Vechev, NeurIPS 2019.

Learning Fast and Precise Numerical Analysis

Jingxuan He, Gagandeep Singh, Markus Püschel, Martin Vechev, PLDI 2020.

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models

Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin Vechev, ICML 2020.

Scaling Polyhedral Neural Network Verification on GPUs

Christoph Müller, Francois Serre, Gagandeep Singh, Markus Püschel, Martin Vechev, MLSys 2021.

Scalable Polyhedral Verification of Recurrent Neural Networks

Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Dan, Martin Vechev, CAV 2021.

Robustness Certification for Point Cloud Models

Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev, ICCV 2021.

FIRE: Enabling Reciprocity for FDD MIMO Systems

Zikun Liu, Gagandeep Singh, Chenren Xu, Deepak Vasisht, MobiCom 2021.

A Dual Number Abstraction for Static Analysis of Clarke Jacobians

Jacob Laurel, Rem Yang, Gagandeep Singh, Sasa Misailovic, POPL 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.

Provably Robust Adversarial Examples

Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev, ICLR 2022.

Shared Certificates for Neural Network Verification

Marc Fischer, Christian Sprecher, Dimitar I. Dimitrov, Gagandeep Singh, Martin Vechev, CAV 2022.

A General Construction for Abstract Interpretation of Higher-Order Automatic Differentiation

Jacob Laurel, Rem yang, Shubham Ugare, Robert Nagel, Gagandeep Singh, Sasa Misailovic, OOPSLA 2022.

Proof Transfer for Fast Certification of Multiple Approximate Neural Networks

Shubham Ugare, Gagandeep Singh, Sasa Misailovic, OOPSLA 2022.

Scalable Verification of GNN-Based Job Schedulers

Haoze Wu, Clark Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh, OOPSLA 2022.

Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems

Zikun Liu, Changming Xu, Gagandeep Singh, and Deepak Vasisht, NSDI 2023.

Provable Defense Against Geometric Transformations

Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh, ICLR 2023 (Spotlight).

Incremental Verification of Neural Networks

Shubham Ugare, Debangshu Banerjee, Sasa Misailovic, and Gagandeep Singh, PLDI 2023.

Synthesizing Precise Static Analyzers for Automatic Differentiation

Jacob Laurel, Siyuan Brant Qian, Gagandeep Singh, Sasa Misailovic, OOPSLA 2023.

Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning

Yinglun Xu, Qi Zeng, Gagandeep Singh, TMLR 2023 (Featured Certification).

Building Trust and Safety in Artificial Intelligence with Abstract Interpretation

Gagandeep Singh, SAS (Invited Abstract) 2023.

Incremental Randomized Smoothing Certification

Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh, and Sasa Misailovic, ICLR 2024.

Dissecting Neural Network Robustness Proofs

Debangshu Banerjee, Avaljot Singh, Gagandeep Singh, ICLR 2024, also at WFVML@ICML 2023 (Outstanding paper).

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler

Zilinghan Li, Pranshu Chaturvedi, Shilan He, Han Chen, Gagandeep Singh, Volodymyr Kindratenko, Eliu A Huerta, Kibaek Kim, Ravi Madduri, ICLR 2024.

COMET: Neural Cost Model Explanation Framework

Isha Chaudhary, Alex Renda, Charith Mendis, Gagandeep Singh, MLSys 2024, also at XAIA@NeurIPS 2023..

talks

teaching

Program Analysis and Synthesis

Graduate course, 2015, 2016

Algorithms and Data Structures

Undergraduate course, 2017

Program Analysis for System Security and Reliability

Graduate course, 2018

Software Engineering Seminar

Undergraduate seminar, 2018

How to Write Fast Numerical Code

Graduate course, 2015, 2016, 2017, 2019

Research Topics in Software Engineering

Graduate seminar, 2016, 2017, 2019

Blockchain Security Seminar

Graduate seminar, 2018, 2019

Reliable and Interpretable Artificial Intelligence

Graduate Course, 2018, 2019

Advanced Systems Lab

Graduate course, 2020

Logic and Artificial Intelligence

Advanced Graduate course, 2021

Overview

Trustworthy AI Systems

Advanced Graduate Course, 2022

Formal Methods for Software Development

Advanced Graduate Course, 2023

Trustworthy AI Systems

Advanced Graduate Course, 2023

Formal Software Development Methods

Advanced Graduate Course, 2024