Saeed Mahloujifar
Princeton University
H-index: 19
North America-United States
Top articles of Saeed Mahloujifar
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
arXiv preprint arXiv:2404.02866
2024/4/3
Privacy Amplification for the Gaussian Mechanism via Bounded Support
arXiv preprint arXiv:2403.05598
2024/3/7
Shengyuan Hu
H-Index: 1
Saeed Mahloujifar
H-Index: 8
Virginia Smith
H-Index: 7
Kamalika Chaudhuri
H-Index: 32
Chuan Guo
H-Index: 2
A Randomized Approach to Tight Privacy Accounting
Advances in Neural Information Processing Systems
2024/2/13
Bounding training data reconstruction in dp-sgd
Advances in Neural Information Processing Systems
2024/2/13
Jamie Hayes
H-Index: 11
Saeed Mahloujifar
H-Index: 8
Private fine-tuning of large language models with zeroth-order optimization
arXiv preprint arXiv:2401.04343
2024/1/9
Horus: Granular {In-Network} Task Scheduler for Cloud Datacenters
2024
A New Linear Scaling Rule for Differentially Private Hyperparameter Optimization
2023/12/12
Experimenting with zero-knowledge proofs of training
2023/11/15
Sanjam Garg
H-Index: 32
Somesh Jha
H-Index: 51
Saeed Mahloujifar
H-Index: 8
Mohammad Mahmoody
H-Index: 17
Mingyuan Wang
H-Index: 3
Publicly detectable watermarking for language models
arXiv preprint arXiv:2310.18491
2023/10/27
Sanjam Garg
H-Index: 32
Somesh Jha
H-Index: 51
Saeed Mahloujifar
H-Index: 8
Mohammad Mahmoody
H-Index: 17
Mingyuan Wang
H-Index: 3
Machine Learning with Feature Differential Privacy
2023/7/21
Multirobustbench: Benchmarking robustness against multiple attacks
2023/7/3
Sihui Dai
H-Index: 2
Saeed Mahloujifar
H-Index: 8
Chong Xiang
H-Index: 3
Vikash Sehwag
H-Index: 7
Prateek Mittal
H-Index: 34
Effectively using public data in privacy preserving machine learning
2023/7/3
Differentially Private Generation of High Fidelity Samples From Diffusion Models
2023/6/23
Vikash Sehwag
H-Index: 7
Ashwinee Panda
H-Index: 1
Saeed Mahloujifar
H-Index: 8
Mung Chiang
H-Index: 48
Prateek Mittal
H-Index: 34
ObjectSeeker: Certifiably robust object detection against patch hiding attacks via patch-agnostic masking
2023/5/21
Uncovering adversarial risks of test-time adaptation
International Conference on Machine Learning (ICML), 2023
2023/1/29
Tong Wu
H-Index: 8
Xiangyu Qi
H-Index: 1
Vikash Sehwag
H-Index: 7
Saeed Mahloujifar
H-Index: 8
Prateek Mittal
H-Index: 34
Towards a proactive {ML} approach for detecting backdoor poison samples
2023
Machine learning with differentially private labels: Mechanisms and frameworks
Proceedings on Privacy Enhancing Technologies
2022
Mitigating membership inference attacks by {Self-Distillation} through a novel ensemble architecture
2022
{PatchCleanser}: Certifiably robust defense against adversarial patches for any image classifier
2022
Dp-raft: A differentially private recipe for accelerated fine-tuning
arXiv preprint arXiv:2212.04486
2022/12/8