Daniel Jones

Principal AI Safety Researcher

Publications

View by:

- Lessons From Red Teaming 100 Generative AI Products
  
  Blake Bullwinkel, Amanda Minnich, Shiven Chawla, Gary Lopez, Martin Pouliot, Whitney Maxwell, Joris de Gruyter, Katherine Pratt, Saphir Qi, Nina Chikanov, Roman Lutz, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Eugenia Kim, Justin Song, Keegan Hines, Daniel Jones, Daniel Jones, Giorgio Severi, Richard Lundeen, Sam Vaughan, Victoria Westerhoff, Pete Bryan, Ram Shankar Siva Kumar, Yonatan Zunger, Chang Kawaguchi, Mark Russinovich
  
  January 2025
  
  DOI PDF
- Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
  
  Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople
  
  Proceedings on Privacy Enhancing Technologies 2024 | June 2024
  
  Publication
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  2023 International Conference on Machine Learning | July 2023
  
  Editor(s): Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication Project
- Training Data Leakage Analysis in Language Models
  
  Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim
  
  February 2021
  
  Preprint

- Lessons From Red Teaming 100 Generative AI Products
  
  Blake Bullwinkel, Amanda Minnich, Shiven Chawla, Gary Lopez, Martin Pouliot, Whitney Maxwell, Joris de Gruyter, Katherine Pratt, Saphir Qi, Nina Chikanov, Roman Lutz, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Eugenia Kim, Justin Song, Keegan Hines, Daniel Jones, Daniel Jones, Giorgio Severi, Richard Lundeen, Sam Vaughan, Victoria Westerhoff, Pete Bryan, Ram Shankar Siva Kumar, Yonatan Zunger, Chang Kawaguchi, Mark Russinovich
  
  January 2025
  
  DOI PDF
- Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
  
  Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople
  
  Proceedings on Privacy Enhancing Technologies 2024 | June 2024
  
  Publication
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  2023 International Conference on Machine Learning | July 2023
  
  Editor(s): Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication Project
- Training Data Leakage Analysis in Language Models
  
  Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim
  
  February 2021
  
  Preprint
- Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
  
  Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople
  
  Proceedings on Privacy Enhancing Technologies 2024 | June 2024
  
  Publication
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  2023 International Conference on Machine Learning | July 2023
  
  Editor(s): Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication Project
- Training Data Leakage Analysis in Language Models
  
  Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim
  
  February 2021
  
  Preprint
- Training Data Leakage Analysis in Language Models
  
  Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim
  
  February 2021
  
  Preprint

- Lessons From Red Teaming 100 Generative AI Products
  
  Blake Bullwinkel, Amanda Minnich, Shiven Chawla, Gary Lopez, Martin Pouliot, Whitney Maxwell, Joris de Gruyter, Katherine Pratt, Saphir Qi, Nina Chikanov, Roman Lutz, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Eugenia Kim, Justin Song, Keegan Hines, Daniel Jones, Daniel Jones, Giorgio Severi, Richard Lundeen, Sam Vaughan, Victoria Westerhoff, Pete Bryan, Ram Shankar Siva Kumar, Yonatan Zunger, Chang Kawaguchi, Mark Russinovich
  
  January 2025
  
  DOI PDF
- Training Data Leakage Analysis in Language Models
  
  Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim
  
  February 2021
  
  Preprint
- Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
  
  Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople
  
  Proceedings on Privacy Enhancing Technologies 2024 | June 2024
  
  Publication
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  2023 International Conference on Machine Learning | July 2023
  
  Editor(s): Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication Project

Daniel Jones

Publications

Lessons From Red Teaming 100 Generative AI Products

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Bayesian Estimation of Differential Privacy

Training Data Leakage Analysis in Language Models

Lessons From Red Teaming 100 Generative AI Products

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Bayesian Estimation of Differential Privacy

Training Data Leakage Analysis in Language Models

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Bayesian Estimation of Differential Privacy

Training Data Leakage Analysis in Language Models

Training Data Leakage Analysis in Language Models

Lessons From Red Teaming 100 Generative AI Products

Training Data Leakage Analysis in Language Models

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Bayesian Estimation of Differential Privacy

Contact Daniel Jones

Microsoft Research Lab – Cambridge