Keynote Speakers

Dr. Alina Oprea (Northeastern University)
Title: Machine Learning Integrity and Privacy in Adversarial Environments
Abstract: Machine learning is increasingly being used for automated decisions in applications such as health care, finance, and personalized recommendations. These critical applications require strong guarantees on both the integrity of the machine learning models and the privacy of the user data used to train these models. The area of adversarial machine learning studies the effect of adversarial attacks against machine learning models and aims to design robust defense algorithms. In this talk I will describe our work on poisoning attacks against machine learning at training time and discuss challenges for creating robust defenses. I will also highlight a surprising connection between machine learning integrity and privacy, and show how poisoning attacks can be used for auditing the privacy of machine learning algorithms.
Speaker's Biography: Alina Oprea is an Associate Professor at Northeastern University in the Khoury College of Computer Sciences. She joined Northeastern University in Fall 2016 after spending 9 years as a research scientist at RSA Laboratories. Her research interests are broadly in cyber security, with a focus on adversarial machine learning, threat detection, cloud security, and applied cryptography. She is the recipient of the Technology Review TR35 award for research in cloud security in 2011 and the recipient of the Google Security and Privacy Award in 2019. Alina serves currently as Program Committee co-chair of the IEEE Security and Privacy Symposium 2021, and as Associate Editor of the ACM Transactions of Privacy and Security (TOPS) journal.

Mr. Dino Cataldo Dell’Accio (United Nations Joint Staff Pension Fund)
Title: Blockchain, biometrics, and geo-location: The United Nations Pension Fund
Abstract: In January 2021, the United Nations Pension Fund (UNJSPF) deployed a solution based on facial recognition and blockchain to reinvent a legacy process with a global audience. The CIO of the UNJSPF will present how the organization formulated the problem to be addressed, developed the approach for its resolution, achieved the intended outcome, and provided relevant security assurance. The solution was selected as a finalist in Gartner’s Eye on Innovation Awards for Government 2020. It was selected as it demonstrated how emerging technology can be combined to allow the service to be delivered in a completely different way, improving integrity and efficiency.
Speaker's Biography: Mr. Dino Cataldo Dell’Accio is the Chief Information Officer of the United Nations Joint Staff Pension Fund (UNJSPF). Before joining the UNJSPF, Mr. Dell’Accio served as Chief of Information and Communications Technology (ICT) Audit in the Office of Internal Oversight Services, and Information Security Officer in the ICT Service Division of the United Nations Secretariat. Previously, he served as Internal Auditor/ICT Auditor in UNICEF.

Dr. Christina Garman (Purdue University)
Title: Privacy, Identity, and Access Control
Abstract: Many notions of access control require some form of identity or identity attributes to mediate access to resources. While this identity does not always correlate directly to a user's real world identity, it may still allow a service provider to build a detailed profile of even the pseudonymous user, including important information that goes beyond that needed to mediate access, such as detailed personal attributes and access patterns, as well as the ability to link resources accessed. In some instances, such information could be quite sensitive if it is ever linked back to the actual user. Even if it is not, as we have seen by the growing interest in privacy and adoption of privacy-enhancing technologies by the general public, users are increasingly asserting their right to privacy and concerned about the collection of their personal information. As such, it is even more important that we consider the privacy implications of all aspects of a system, including identity and access control. In this talk, I will provide an overview of a few existing cryptographic techniques that I believe are relevant to this space, particularly in enabling anonymous or privacy-preserving access control mechanisms. As part of this, I will highlight some of my prior work on decentralizing anonymous credentials in an effort to eliminate one of the major barriers to deployment of such systems. I will also discuss successful deployments of some of these technologies, such as Cloudflare's Privacy Pass. I will conclude by examining what I see as some of the challenges and open problems pertaining to privacy and identity and how these relate to the field of access control.
Speaker's Biography: Christina Garman is an assistant professor in the Department of Computer Science at Purdue University. Her research interests focus largely on practical and applied cryptography, namely the design and analysis of real world cryptographic systems. She aims to make it easier to design and securely deploy new and complex cryptographic systems while preventing insecurities from occurring in such systems. As part of this, her work thus far has been on both building and deploying secure cryptographic systems, as well as analyzing existing systems. This includes past work on cryptographic automation and building "keyless CDNs", as well as exploring the weaknesses of RC4 in TLS and discovering flaws in Apple's iMessage, and her current work focusing on removing the "human element" from the deployment and analysis of cryptographic systems through the use of cryptographic automation and the development of tools. She received an NSF CAREER Award in 2021, and her work has received a best paper award at ACM CCS and been featured in numerous media, including The Washington Post, The New York Times, Wired, and The Economist. She is also one of the co-founders of Zcash, a privacy preserving cryptocurrency based on her work on Zerocash. She received her MS and Ph.D. from Johns Hopkins University in Computer Science in 2013 and 2017 respectively, and a BS in Computer Science Engineering and a BA Mathematics, with a minor in Physics, from Bucknell University in 2011.