Nathalie Baracaldo

Nathalie Baracaldo leads the AI Security and Privacy Solutions team and is a Research Staff Member at IBM’s Almaden Research Center in San Jose, CA. Nathalie is passionate about delivering machine learning solutions that are highly accurate, withstand adversarial attacks and protect data privacy. Her team focuses on two main areas: federated learning, where models are trained without directly accessing training data and adversarial machine learning, where defenses are designed to withstand potential attacks to the machine learning pipeline (see more details).

Nathalie is the primary investigator for the DARPA program Guaranteeing AI Robustness Against Deception (GARD), where AI security is investigated. Her team contributes to the Adversarial Robustness 360 Toolbox (ART).

Nathalie's primary research interests lie at the intersection of information security, privacy and trust. As part of her work, she has also designed and implemented secure systems in the areas of cloud computing, Platform as a Service, secure data sharing and Internet of the Things. She has also contributed to projects to design scalable systems that monitor, manage performance and manage service level agreements in cloud environments.

In 2020, Nathalie received the IBM Master Inventor distinction for her contributions to the IBM Intellectual Property and innovation.  Nathalie also received the 2021 Corporate Technical Recognition, one of the highest recognitions provided to IBMers for breakthrough technical achievements that have led to notable market and industry success for IBM. This recognition was awarded for Nathalie's contribution to the Trusted AI initiative. 

Nathalie is associated Editor IEEE Transactions on Service Computing.

Nathalie received her Ph.D. degree from the University of Pittsburgh in 2016. Her dissertation focused on preventing insider threats through the use of adaptive access control systems that integrate multiple sources of contextual information. Some of the topics that she has explored in the past include secure storage systems, privacy in online social networks, secure interoperability in distributed systems, risk management and trust evaluation. During her Ph.D. studies she received the 2014 Allen Kent Award for Outstanding Contributions to the Graduate Program in Information Science by the School of Information Sciences at the University of Pittsburgh.

Nathalie also holds a master’s degree with Cum Laude distinction in computer sciences from the Universidad de los Andes, Colombia. Prior to that, she earned two undergraduate degrees in Computer Science and Industrial Engineering at the same university.

A few other highlights  

• Check our IBM Federated Learning library (IBM FL) 

• Check our Adversarial Robustness Toolbox (ART)

• Invited tutorial: IEEE TPS 2021 https://www.sis.pitt.edu/lersais/conference/cic/2021/tutorials.html 

• Keynote @ EMISA 2021

• Data Science Podcast - Federated learning, special guest Nathalie Baracaldo 

• Check my blog post on Accountable federated learning German version  and English version

• I am associated Editor IEEE Transactions on Service Computing

• Guest editor for the Special Issue on ML Security and Privacy at the IEEE S&P Magazine

• IEEE Symposium on Security and Privacy: 

  • Publication Chair (S&P2022)
  • Poster Chair (S&P 2021) 

• Organizing commetee member of the following federated learning workshops:

  •  MLSys CrossFL 2022
  •  ICML-FL2021
  •  ICML-FL2020

• Advisor for the Workshop for Establishing the Roadmap for Security, Privacy, and Ethics in Health and Biomedical Research, 2021 

• NeurIPs 2020 Beyond AutoML: Scaling & Automating AI, Lisa Amini, Nathalie Baracaldo, et al presentation

• Interview on Federated Learning and Adversarial ML DC_THURS: https://www.youtube.com/watch?v=dxWCoBFv1QY

• My papers: check the following tab or google scholar 

• My patents: google patents (I don't update the tab in this web page)