Picture for Mohammad Mahmoody

Mohammad Mahmoody

Publicly Detectable Watermarking for Language Models

Add code
Oct 27, 2023
Figure 1 for Publicly Detectable Watermarking for Language Models
Figure 2 for Publicly Detectable Watermarking for Language Models
Figure 3 for Publicly Detectable Watermarking for Language Models
Figure 4 for Publicly Detectable Watermarking for Language Models
Viaarxiv icon

On Optimal Learning Under Targeted Data Poisoning

Add code
Oct 12, 2022
Figure 1 for On Optimal Learning Under Targeted Data Poisoning
Figure 2 for On Optimal Learning Under Targeted Data Poisoning
Viaarxiv icon

Overparameterized (robust) models from computational constraints

Add code
Aug 27, 2022
Viaarxiv icon

Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning

Add code
Feb 07, 2022
Figure 1 for Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Figure 2 for Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Figure 3 for Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Figure 4 for Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Viaarxiv icon

Learning and Certification under Instance-targeted Poisoning

Add code
May 18, 2021
Figure 1 for Learning and Certification under Instance-targeted Poisoning
Figure 2 for Learning and Certification under Instance-targeted Poisoning
Figure 3 for Learning and Certification under Instance-targeted Poisoning
Viaarxiv icon

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?

Add code
Nov 10, 2020
Figure 1 for An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
Figure 2 for An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
Figure 3 for An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
Figure 4 for An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
Viaarxiv icon

Obliviousness Makes Poisoning Adversaries Weaker

Add code
Mar 26, 2020
Figure 1 for Obliviousness Makes Poisoning Adversaries Weaker
Figure 2 for Obliviousness Makes Poisoning Adversaries Weaker
Figure 3 for Obliviousness Makes Poisoning Adversaries Weaker
Figure 4 for Obliviousness Makes Poisoning Adversaries Weaker
Viaarxiv icon

Computational Concentration of Measure: Optimal Bounds, Reductions, and More

Add code
Jul 11, 2019
Viaarxiv icon

Lower Bounds for Adversarially Robust PAC Learning

Add code
Jun 13, 2019
Viaarxiv icon

Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness

Add code
May 29, 2019
Figure 1 for Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Figure 2 for Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Figure 3 for Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Figure 4 for Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Viaarxiv icon