Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Matthew Jagielski

Matthew Jagielski

Extracting Training Data from Large Language Models


Dec 14, 2020
Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea, Colin Raffel

Figure 1 for Extracting Training Data from Large Language Models
Figure 2 for Extracting Training Data from Large Language Models
Figure 3 for Extracting Training Data from Large Language Models
Figure 4 for Extracting Training Data from Large Language Models

  Access Paper or Ask Questions

Subpopulation Data Poisoning Attacks


Jun 24, 2020
Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger, Alina Oprea

Figure 1 for Subpopulation Data Poisoning Attacks
Figure 2 for Subpopulation Data Poisoning Attacks
Figure 3 for Subpopulation Data Poisoning Attacks

  Access Paper or Ask Questions

Auditing Differentially Private Machine Learning: How Private is Private SGD?


Jun 13, 2020
Matthew Jagielski, Jonathan Ullman, Alina Oprea

Figure 1 for Auditing Differentially Private Machine Learning: How Private is Private SGD?
Figure 2 for Auditing Differentially Private Machine Learning: How Private is Private SGD?
Figure 3 for Auditing Differentially Private Machine Learning: How Private is Private SGD?
Figure 4 for Auditing Differentially Private Machine Learning: How Private is Private SGD?

  Access Paper or Ask Questions

Cryptanalytic Extraction of Neural Network Models


Mar 10, 2020
Nicholas Carlini, Matthew Jagielski, Ilya Mironov

Figure 1 for Cryptanalytic Extraction of Neural Network Models
Figure 2 for Cryptanalytic Extraction of Neural Network Models
Figure 3 for Cryptanalytic Extraction of Neural Network Models
Figure 4 for Cryptanalytic Extraction of Neural Network Models

  Access Paper or Ask Questions

High-Fidelity Extraction of Neural Network Models


Sep 03, 2019
Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, Nicolas Papernot

Figure 1 for High-Fidelity Extraction of Neural Network Models
Figure 2 for High-Fidelity Extraction of Neural Network Models
Figure 3 for High-Fidelity Extraction of Neural Network Models
Figure 4 for High-Fidelity Extraction of Neural Network Models

  Access Paper or Ask Questions

Differentially Private Fair Learning


Dec 06, 2018
Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi-Malvajerdi, Jonathan Ullman

Figure 1 for Differentially Private Fair Learning
Figure 2 for Differentially Private Fair Learning
Figure 3 for Differentially Private Fair Learning

  Access Paper or Ask Questions

On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks


Sep 08, 2018
Ambra Demontis, Marco Melis, Maura Pintor, Matthew Jagielski, Battista Biggio, Alina Oprea, Cristina Nita-Rotaru, Fabio Roli

Figure 1 for On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
Figure 2 for On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
Figure 3 for On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
Figure 4 for On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks

  Access Paper or Ask Questions

Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning


Apr 01, 2018
Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita-Rotaru, Bo Li

Figure 1 for Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Figure 2 for Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Figure 3 for Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Figure 4 for Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
* Preprint of the work accepted for publication at the 39th IEEE Symposium on Security and Privacy, San Francisco, CA, USA, May 21-23, 2018 
  Access Paper or Ask Questions