publications

2025

1. Sentry: Authenticating Machine Learning Artifacts on the Fly

   Andrew Gan and Zahra Ghodsi

   In Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2025

   HTML
2. AnoFel: Supporting Anonymity for Privacy-preserving Federated Learning

   Ghada Almashaqbeh and Zahra Ghodsi

   In Privacy Enhancing Technologies Symposium (PETS), 2025

   HTML
3. cuOT: Accelerating Oblivious Transfer on Gpus for Privacy-Preserving Computation

   Andrew Gan, Setsuna Yuki, Timothy Rogers, and 1 more author

   In IEEE International Symposium on Hardware Oriented Security and Trust (HOST), 2025

   HTML

2023

1. Zkrownn: Zero Knowledge Right of Ownership for Neural Networks

   Nojan Sheybani, Zahra Ghodsi, Ritvik Kapila, and 1 more author

   In ACM/IEEE Design Automation Conference (DAC), 2023
2. AdaGL: Adaptive Learning for Agile Distributed Training of Gigantic GNNs

   Ruisi Zhang, Mojan Javaheripi, Zahra Ghodsi, and 2 more authors

   In ACM/IEEE Design Automation Conference (DAC), 2023
3. Characterizing and Optimizing end-to-end Systems for Private Inference

   Karthik Garimella, Zahra Ghodsi, Nandan Kumar Jha, and 2 more authors

   In ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3, 2023
4. zPROBE: Zero Peek Robustness Checks for Federated Learning

   Zahra Ghodsi, Mojan Javaheripi, Nojan Sheybani, and 3 more authors

   In IEEE/CVF International Conference on Computer Vision, 2023

2022

1. Sphynx: A Deep Neural Network Design for Private Inference

   Minsu Cho, Zahra Ghodsi, Brandon Reagen, and 2 more authors

   IEEE Security & Privacy, 2022

2021

1. Circa: Stochastic ReLUs for Private Deep Learning

   Zahra Ghodsi, Nandan Kumar Jha, Brandon Reagen, and 1 more author

   Advances in Neural Information Processing Systems (NeurIPS), 2021
2. Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

   Zahra Ghodsi, Siva Kumar Sastry Hari, Iuri Frosio, and 5 more authors

   In IEEE Intelligent Vehicles Symposium (IV), 2021
3. Deepreduce: Relu Reduction for Fast Private Inference

   Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, and 1 more author

   In International Conference on Machine Learning (ICML), 2021

2020

1. SafeTPU: A Verifiably Secure Hardware Accelerator for Deep Neural Networks

   Maria I Mera Collantes, Zahra Ghodsi, and Siddharth Garg

   In IEEE VLSI Test Symposium (VTS), 2020
2. Cryptonas: Private Inference on a ReLU Budget

   Zahra Ghodsi, Akshaj Kumar Veldanda, Brandon Reagen, and 1 more author

   Advances in Neural Information Processing Systems (NeurIPS), 2020

2019

1. Enabling timing error resilience for low-power systolic-array based deep learning accelerators

   Jeff Zhang, Zahra Ghodsi, Siddharth Garg, and 1 more author

   IEEE Design & Test, 2019

2018

1. Thundervolt: enabling aggressive voltage underscaling and timing error resilience for energy efficient deep learning accelerators

   Jeff Zhang, Kartheek Rangineni, Zahra Ghodsi, and 1 more author

   In IEEE/ACM Design Automation Conference (DAC), 2018

2017

1. Optimal checkpointing for secure intermittently-powered IoT devices

   Zahra Ghodsi, Siddharth Garg, and Ramesh Karri

   In IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2017
2. SafetyNets: Verifiable Execution of Deep Neural Networks on an Nntrusted Cloud

   Zahra Ghodsi, Tianyu Gu, and Siddharth Garg

   Advances in Neural Information Processing Systems (NeurIPS), 2017