| Safetynets: Verifiable execution of deep neural networks on an untrusted cloud Z Ghodsi, T Gu, S Garg 31st Conference on Neural Information Processing Systems (NIPS 2017), 2017 | 124 | 2017 |
| Thundervolt: enabling aggressive voltage underscaling and timing error resilience for energy efficient deep learning accelerators J Zhang, K Rangineni, Z Ghodsi, S Garg Proceedings of the 55th Annual Design Automation Conference, 19, 2018 | 122 | 2018 |
| Cryptonas: Private inference on a relu budget Z Ghodsi, A Veldanda, B Reagen, S Garg 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020 | 39 | 2020 |
| DeepReDuce: Relu reduction for fast private inference NK Jha, Z Ghodsi, S Garg, B Reagen International Conference on Machine Learning, 4839-4849, 2021 | 29 | 2021 |
| Optimal checkpointing for secure intermittently-powered IoT devices Z Ghodsi, S Garg, R Karri 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 376-383, 2017 | 22 | 2017 |
| Circa: Stochastic relus for private deep learning Z Ghodsi, NK Jha, B Reagen, S Garg Advances in Neural Information Processing Systems 34, 2241-2252, 2021 | 12 | 2021 |
| Generating and characterizing scenarios for safety testing of autonomous vehicles Z Ghodsi, SKS Hari, I Frosio, T Tsai, A Troccoli, SW Keckler, S Garg, ... 2021 IEEE Intelligent Vehicles Symposium (IV), 157-164, 2021 | 12 | 2021 |
| Enabling timing error resilience for low-power systolic-array based deep learning accelerators J Zhang, Z Ghodsi, S Garg, K Rangineni IEEE Design & Test 37 (2), 93-102, 2019 | 12 | 2019 |
| Safetpu: A verifiably secure hardware accelerator for deep neural networks MIM Collantes, Z Ghodsi, S Garg 2020 IEEE 38th VLSI Test Symposium (VTS), 1-6, 2020 | 9 | 2020 |
| Sphynx: A Deep Neural Network Design for Private Inference M Cho, Z Ghodsi, B Reagen, S Garg, C Hegde IEEE Security & Privacy 20 (5), 22-34, 2022 | 8 | 2022 |
| Outsourcing private machine learning via lightweight secure arithmetic computation S Garg, Z Ghodsi, C Hazay, Y Ishai, A Marcedone, ... arXiv preprint arXiv:1812.01372, 2018 | 4 | 2018 |
| Characterizing and optimizing end-to-end systems for private inference K Garimella, Z Ghodsi, NK Jha, S Garg, B Reagen arXiv preprint arXiv:2207.07177, 2022 | 2 | 2022 |
| Cryptonite: Revealing the pitfalls of end-to-end private inference at scale K Garimella, NK Jha, Z Ghodsi, S Garg, B Reagen arXiv preprint arXiv:2111.02583, 2021 | 1 | 2021 |
| Secure Frameworks for Outsourced Deep Learning Inference Z Ghodsi New York University Tandon School of Engineering, 2021 | 1 | 2021 |
| Adversarial scenarios for safety testing of autonomous vehicles SKS Hari, I Frosio, Z Ghodsi, A Anandkumar, T Tsai, SW Keckler, ... US Patent 11,550,325, 2023 | | 2023 |
| Tensor-based driving scenario characterization SKS Hari, I Frosio, Z Ghodsi, A Anandkumar, T Tsai, SW Keckler US Patent 11,390,301, 2022 | | 2022 |
| zPROBE: Zero Peek Robustness Checks for Federated Learning Z Ghodsi, M Javaheripi, N Sheybani, X Zhang, K Huang, F Koushanfar arXiv preprint arXiv:2206.12100, 2022 | | 2022 |
