Alert button
Picture for Gautam Kamath

Gautam Kamath

Alert button

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors

Feb 20, 2024
Yiwei Lu, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu

Viaarxiv icon

Not All Learnable Distribution Classes are Privately Learnable

Feb 05, 2024
Mark Bun, Gautam Kamath, Argyris Mouzakis, Vikrant Singhal

Viaarxiv icon

Private Distribution Learning with Public Data: The View from Sample Compression

Aug 14, 2023
Shai Ben-David, Alex Bie, Clément L. Canonne, Gautam Kamath, Vikrant Singhal

Viaarxiv icon

Exploring the Limits of Indiscriminate Data Poisoning Attacks

Mar 08, 2023
Yiwei Lu, Gautam Kamath, Yaoliang Yu

Figure 1 for Exploring the Limits of Indiscriminate Data Poisoning Attacks
Figure 2 for Exploring the Limits of Indiscriminate Data Poisoning Attacks
Figure 3 for Exploring the Limits of Indiscriminate Data Poisoning Attacks
Figure 4 for Exploring the Limits of Indiscriminate Data Poisoning Attacks
Viaarxiv icon

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance

Mar 02, 2023
Xin Gu, Gautam Kamath, Zhiwei Steven Wu

Figure 1 for Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Figure 2 for Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Figure 3 for Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Figure 4 for Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Viaarxiv icon

Private GANs, Revisited

Feb 06, 2023
Alex Bie, Gautam Kamath, Guojun Zhang

Figure 1 for Private GANs, Revisited
Figure 2 for Private GANs, Revisited
Figure 3 for Private GANs, Revisited
Figure 4 for Private GANs, Revisited
Viaarxiv icon

A Bias-Variance-Privacy Trilemma for Statistical Estimation

Jan 30, 2023
Gautam Kamath, Argyris Mouzakis, Matthew Regehr, Vikrant Singhal, Thomas Steinke, Jonathan Ullman

Viaarxiv icon

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

Dec 21, 2022
Jimmy Z. Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, Ayush Sekhari

Figure 1 for Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Figure 2 for Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Figure 3 for Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Figure 4 for Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Viaarxiv icon