Gautam Kamath

National Institute of Technology Karnataka — India

Computer Science · Physical Sciences

20h-index1.4kcitations114works3.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(52), Machine Learning and Algorithms(36), Cryptography and Data Security(26), Adversarial Robustness in Machine Learning(25), Stochastic Gradient Optimization Techniques(14)

Publications114 total

Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
arXiv (Cornell University)·2025Open Access
Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning
arXiv (Cornell University)·2025Open Access
The Broader Landscape of Robustness in Algorithmic Statistics
IEEE BITS the Information Theory Magazine·2025
On the Learnability of Distribution Classes with Adaptive Adversaries
arXiv (Cornell University)·2025Open Access
Data Privacy and Ethics on Social Media Platforms
2025
Position: Membership Inference Attacks Cannot Prove That a Model was Trained on Your Data
2025· 3 cited
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
2025· 1 cited
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms Under Composition
2025Open Access
Optimal Differentially Private Sampling of Unbounded Gaussians
arXiv (Cornell University)·2025Open Access
Private Mean Estimation with Person-Level Differential Privacy
Society for Industrial and Applied Mathematics eBooks·2025· 4 cited
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
arXiv (Cornell University)·2024Open Access
A Bias-Accuracy-Privacy Trilemma for Statistical Estimation
Journal of the American Statistical Association·2024
The Broader Landscape of Robustness in Algorithmic Statistics
arXiv (Cornell University)·2024Open Access
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
arXiv (Cornell University)·2024Open Access
Machine Unlearning Fails to Remove Data Poisoning Attacks
arXiv (Cornell University)·2024Open Access
Distribution Learnability and Robustness
arXiv (Cornell University)·2024Open Access
Differentially Private Fine-tuning of Language Models
Journal of Privacy and Confidentiality·2024· 33 citedOpen Access
Private Mean Estimation with Person-Level Differential Privacy
arXiv (Cornell University)·2024Open Access
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
arXiv (Cornell University)·2024Open Access
Not All Learnable Distribution Classes are Privately Learnable
2024Open Access
page 1 of 6Next →

Frequent Co-authors

Constantinos Daskalakis(9), Jayadev Acharya(8), Ilias Diakonikolas(7), Daniel M. Kane(7), Alistair Stewart(7), Jonathan Ullman(7), Jerry Li(6), Ankur Moitra(5), Clément L. Canonne(5), Vikrant Singhal(5), Sivakanth Gopi(4), Janardhan Kulkarni(4), Sergey Yekhanin(4), Huanyu Zhang(4), Thomas Steinke(3), Zhiwei Steven Wu(3), Jacob Steinhardt(2), Jerry Li(2), Ayush Sekhari(2), Dahua Yu(2)