Upcoming Events:
LERSAIS/DINS/DOCTORAL GUILD SEMINAR
Demystifying Safety in Generative AI: From Alignment to Policy Enforcement
Nathalie Baracaldo, PhD
Senior Research Scientist and Master Inventor, IBM Research
Alumna, IS PhD Program
Friday, September 25, 2026
1:00 – 2:00 pm
Room 316 (Third Floor) IS Building, 135 North Bellefield Avenue, Pittsburgh, PA 15213
As agentic AI systems proliferate and large language models become ubiquitous, ensuring AI safety has never been more critical, and at the same time, more complex. Safeguarding generative AI requires addressing risks across multiple layers: data curation, training methodology, model harness design, and deployment infrastructure.
This talk examines key aspects of the AI training process, focusing on alignment techniques and unlearning mechanisms, then turns to a critical challenge: policy enforcement in enterprise GenAI systems. I will highlight discrepancies in what policy means to different communities and some of the very different ways policies are enforced in each silo. After that, I will explain common pitfalls that practitioners encounter and offer concrete recommendations for building safer systems.
Nathalie Baracaldo is a Senior Research Scientist and Master Inventor at IBM Research in San Jose, California, where her work focuses on building trustworthy AI systems. She has extensive experience delivering impactful machine learning solutions that are highly accurate, withstand adversarial attacks, and protect data privacy. Her current research focuses on safeguarding generative AI through unlearning and alignment techniques. She served as the principal investigator for the DARPA GARD program, leading efforts to extend and maintain the Adversarial Robustness Toolbox (ART) for red teaming evaluations. She also led IBM's federated learning initiative and co-edited two books: "Federated Learning: A Comprehensive Overview of Methods and Applications" (Springer, 2022) and "Machine Unlearning for Governance of Foundation Models" (2026). Her research has been published in top AI and security conferences, earning multiple best paper awards and thousands of citations. She received the IBM Master Inventor distinction in 2020 and the Corporate Technical Recognition in 2021. She holds a Ph.D. from the University of Pittsburgh.
Brought to you by the Laboratory of Education and Research on Security Assured Information Systems (LERSAIS), the Department of Informatics and Networked Systems, and the Doctoral Guild at Pitt.
PREVIOUS EVENTS:
SCI, LERSAIS and Pitt Cyber DISTINGUISHED INDUSTRY SPEAKER
Thursday, June 26, 2025
Driving Sustainable Innovation in Electronics: TDK’s Digital Transformation Initiatives
Roshan Thapliya, PhD
TDK Corporation, Corporate Officer, Chief Digital Transformation Officer (CDXO); GM, Management Systems HQ & DX Promotion Grp.
11 am - 12 pm
Room 5317 Sennott Square, 210 South Bouquet Street, Pittsburgh 15213
Abstract: This talk presents TDK Group’s ongoing journey toward innovation and sustainability, guided by our long-term vision—“TDK Transformation.” As a global leader in electronic components and solutions, TDK is committed to shaping a better future by integrating advanced digital tools, automated manufacturing, and materials science to accelerate innovation. The presentation will explore TDK’s dual focus on green transformation (GX), including decarbonization and energy storage, and digital transformation (DX), leveraging artificial intelligence and automation to drive operational efficiency and societal progress. Key topics include TDK’s strategic strengths, TDK’s approach to DX, the implementation of advanced AI platforms and agentic AI systems, the development of next-generation DX/AI-driven electronics, human upskilling through employee engagement, cybersecurity resilience, and recent new business initiatives. Attendees will gain insights into how TDK is advancing innovation and sustainability through technology, and how these efforts are shaping the future of the electronics industry.
Bio: Roshan Thapliya, PhD, is the Chief Digital Transformation Officer (CDXO), and General 
Manager of the Management Systems HQ (Global IT/Digital HQ) at TDK Corporation, Tokyo—a global leader in electronic components and smart technologies. He drives the company’s global IT and digital transformation (DX) strategy, with a sharp focus on integrating AI, cybersecurity, IoT, and next-generation digital solutions into industrial ecosystems worldwide. With over two decades of leadership experience in Japan’s innovation ecosystem, he previously spent nearly 23 years at FUJIFILM Business Innovation (formerly Fuji Xerox), and BRIDGESTONE Corporation where he led pioneering work in digital systems, robotics, AI, user experience design, data analytics and new business innovation before his current position in TDK. He has published extensively in leading journals and served as an Advisory Board Member for the National Facility for HRI Research at the University of New South Wales, Australia. He has been invited as invited/keynote speaker in various academic societies, such as IEEE, and academic institutions, holds 35+ international patents and a BEng ('94), MEng('96) and PhD('99) in Electronics Engineering/Photonics from The University of Tokyo.
Friday, April 18, 2025
The Economics of Privacy at a Crossroads
Alessandro Acquisti, Trustees Professor of Information Technology and Public Policy
Heinz College, Carnegie Mellon University
12:00 - 1:00 pm
Fifth Floor Conference Rooms in 130 North Bellefield Avenue, Pittsburgh, 15213
Abstract: I will consider the past, present, and possible futures of the economics of privacy. First, I will review the rise of this field of research up to the current days, and celebrate its successes. Next, I will take stock of the present and focus on the unintended consequences of those successes: I will highlight possible shortcomings of the economics of privacy that arise from its dismissal of critical privacy theories from other social sciences. Finally, I will consider a possible alternative future for the economics of privacy. I will propose ways of framing the economic debate around privacy that deviate from the focus of much (albeit not all) current research, which tends to concentrate on the economic costs of privacy protection at the expense of a richer array of yet unanswered questions.
Bio: Alessandro Acquisti is Trustees Professor of Information Technology and Public Policy at Carnegie Mellon University's Heinz College, and the co-director of the CMU Center for Behavioral Decision Research (CBDR). He is a fellow of the Ponemon Institute and a member of Carnegie Mellon CyLab and the CyLab Usability, Privacy, and Security (CUPS) lab.
Alessandro’s research investigates the economics and behavioral economics of privacy, and privacy in online social networks. His studies have been published in leading journals across diverse disciplines (such as Proceedings of the National Academy of Science, Journal of Consumer Research, Marketing Science, Information Systems Research, Journal of Comparative Economics, ACM Transactions on the Internet), as well as edited books, book chapters, conference proceedings, and numerous international keynotes.
Alessandro has been the recipient of the PET Award for Outstanding Research in Privacy Enhancing Technologies, the IBM Best Academic Privacy Faculty Award, the Heinz College’s School of Information Teaching Excellent Award, and various best paper awards. He has been awarded research grants from the National Science Foundation, Transcoop Foundation, Google, and Microsoft. He has been invited to be part of the Federal Trade Commission’s Privacy Roundtables and to co-chair the Cyber-Economics Track at the "National Cyber Leap Year Summit,” as part of the NITRD Program under guidance from the White House Office of Science and Technology Policy. He is a member of the National Academy of Science’s Committee on Public Response to Alerts and Warnings Using Social Media and Associated Privacy Considerations.
Friday, April 11, 2025
Designing Usable and Useful Privacy Interfaces
Lorrie Cranor, Director and Bosch Distinguished Professor in Security and Privacy Technologies of CyLab
FORE Systems University Professor of Computer Science and of Engineering and Public Policy
Carnegie Mellon University
12 noon to 1:00 pm
Third Floor Student Center, IS Building, 135 North Bellefield Avenue, Pittsburgh, PA 15213
Abstract: Users who wish to exercise privacy rights or make privacy choices must often rely on website or app user interfaces. However, too often, these user interfaces suffer from usability deficiencies ranging from being difficult to find, hard to understand, or time-consuming to use, to being deceptive and dangerously misleading. This talk will discuss user-centric approaches to designing and evaluating privacy interfaces that better meet user needs and reduce the overwhelming number of privacy choices. I'll present a privacy choice mechanism evaluation framework and several examples of privacy interface design and evaluation from my research, including more usable cookie consent banners, mobile app privacy nutrition labels, IoT privacy and security labels, and a privacy options icon for the State of California.
Bio: Lorrie Faith Cranor (lorrie.cranor.org) is the Director and Bosch Distinguished Professor in Security and Privacy Technologies of CyLab and the FORE Systems University Professor of Computer Science and of Engineering and Public Policy at Carnegie Mellon University. She directs the CyLab Usable Privacy and Security Laboratory (CUPS) and co-directs the Privacy Engineering masters program. In 2016 she served as Chief Technologist at the US Federal Trade Commission. She is also a co-founder of Wombat Security Technologies, Inc, a security awareness training company that was acquired by Proofpoint. She founded the Symposium On Usable Privacy and Security (SOUPS) and co-founded the Conference on Privacy Engineering Practice and Respect (PEPR). She has served on a number of boards, including the Electronic Frontier Foundation Board of Directors, the Center for Democracy and Technology Board of Directors, the Electronic Privacy Information Center Advisory Board, the Computing Research Association Board of Directors, and the Aspen Institute Cybersecurity Group. She was elected to the ACM CHI Academy and named a Fellow of
IEEE, ACM, and AAAS. She was previously a researcher at AT&T-Labs Research. She holds a doctorate in Engineering and Policy from
Washington University in St. Louis. She plays soccer, walks to work, sews her own clothing with pockets, and tries not to embarrass her three young adult children.
Friday, April 4, 2025
Privacy, Learning and Inference
Adam Smith, Professor of Computer Science, Boston University
Abstract: How can we train machine learning models while keeping confidential the information of individuals who contributed training data? The last decade has seen an explosion in the scale and reach of machine learning, as well as the importance of sensitive individual data—medical records, census answers, ad viewing, for example—in ML deployments.
This talk discusses the possibilities and limitations of fitting machine learning and statistical models while protecting the privacy of individual records. I will begin by explaining what makes this problem difficult, using recent examples of training-data memorization and other breaches. I will present differential privacy, a rigorous definition of privacy in statistical databases that is now widely studied, and increasingly used to analyze and design deployed systems.
Time permitting, I will also present recent algorithmic results on two basic problems: differentially private mean estimation and linear regression. We give efficient and (nearly) sample-optimal algorithms for solving these when the training data are "nicely" distributed.
Bio: Adam Smith is a professor of computer science at Boston University. From 2007 to 2017, he served on the faculty of the Computer Science and Engineering Department at Penn State. His research interests lie in data privacy and cryptography, and their connections to machine learning, statistics, information theory, and quantum computing. He obtained his Ph.D. from MIT in 2004 and has held postdoc and visiting positions at the Weizmann Institute of Science, UCLA, Boston University and Harvard. His work received a Presidential Early Career Award for Scientists and Engineers (PECASE) in 2009; a Theory of Cryptography Test of Time award in 2016; the Eurocrypt 2019 Test of Time award; the 2017 Gödel Prize; and the 2021 Kanellakis Theory and Practice Award. He is a Fellow of the ACM.
Thursday, March 13, 2025
DINS+LERSAIS+PittCyber Seminar
Advanced Privacy-Preserving Federated Learning as a Service (APPFLx): Building Robust and Trustworthy AI Models
Ravi K. Madduri, Senior Computer Scientist
Data Science and Learning Division
Argonne National Laboratory
Abstract: Conducting secure privacy-preserving federated learning (PPFL) experiments that leverage large-scale, high-performance computational resources across distributed sites often demands technical capabilities beyond the reach of many organizations. To lower the barrier to entry for PPFL and empower domain experts in large institutions to utilize federated learning (FL), we developed Advanced Privacy-Preserving Federated Learning as a Service (APPFLx). APPFLx simplifies cross-silo PPFL through an intuitive web interface for managing, deploying, analyzing, and visualizing FL experiments.
The platform ensures secure federations using robust, end-to-end Identity and Access Management. Participants can establish or join federations using institutional credentials, perform privacy-preserving training on local datasets, and securely share model updates for aggregation. Additionally, we present the AI Data Readiness Inspector (AIDRIN) framework, designed to assess dataset readiness for AI applications, incorporating both traditional data quality metrics and AI-specific considerations. We discuss how integrating AIDRIN with APPFLx enhances data preparation and facilitates improved FL experiments, fostering trustworthy and effective AI model development.
Bio: Ravi is a computer scientist working in the intersection of HPC/AI and biomedicine. His research interests are in building sustainable, scalable services for science, reproducible research, large-scale data management, analysis using HPC and AI. He leads the PALISADE-X project that is developing Privacy-preserving Federated Learning framework to build robust, trust-worthy AI models. He co-leads the MVP-CHAMPION project, which is a collaboration between VA and DOE and develops methods to perform large-scale genetic data analysis using DOE’s high performance computing capabilities, including methods for generating PRS scores in Prostate Cancer, genome-wide PheWAS on Summit supercomputer. Additionally, Ravi is one of three key contributors to the National Institutes of Health $100M Cancer Biomedical Informatics Grid (caBIG), which linked 60 NIH-funded cancer centers and clinical sites engaged in cancer research. For his efforts in project management, tool development, and collaboration, Ravi received several Outstanding Achievement Awards from NIH. For his work on “Cancer Moonshot” project, he received the Department of Energy Secretary award in 2017.
Friday, January 31, 2025
DINS+LERSAIS+PittCyber Seminar
Trustworthy Artificial Intelligence for Securing Transportation Systems
Dr. Bhavani Thuraisingham, The University of Texas at Dallas
Abstract: Artificial Intelligence (AI) techniques ae being applied to numerous applications from Healthcare to Cyber Security to Finance. For example, Machine Learning (ML) algorithms are being applied to solve security problems such as malware analysis and insider threat detection. However, there are many challenges in applying ML algorithms for various applications. For example, (i) the ML algorithms may violate the privacy of individuals. This is because we can gather massive amounts of data and apply ML algorithms on the data to extract highly sensitive information. (ii) ML algorithms may show bias and be unfair to various segments of the population. (iii) ML algorithms themselves may be attacked possibly resulting in catastrophic errors including in cyber physical systems such as transportation systems.
In this presentation, we discuss our research we are conducting as part of the USDOT National University Technology Center TraCR (Transportation Cybersecurity and Resiliency) led by Clemson University. In particular, we describe (i) the application of federated machine learning techniques for detecting attacks in transportation systems; (ii) publishing synthetic transportation data sets that preserves privacy, (iii) fairness algorithms for transportation systems, and (iv) examining how GenAI systems are being integrated with transportation systems to provide security. Finally we discuss resiliency issues with respect to transportation systems where such systems and applications must continue to operate in the midst of attacks and failures.
Bio: Dr. Bhavani Thuraisingham is the Founders Chair Professor of Computer Science and the Founding Executive Director of the Cyber Security Research and Education Institute at the University of Texas at Dallas (UTD). She is an elected Fellow of the ACM, IEEE, the AAAS, and the NAI. Her research interests are integrating cyber security and artificial intelligence/data science including as they relate to the cloud, social media, and Transportation Systems. She has received several technical, education and leadership awards including the IEEE CS 1997 Edward J. McCluskey Technical Achievement Award, the IEEE CS 2023 Taylor L. Booth Education Award, ACM SIGSAC 2010 Outstanding Contributions Award, the IEEE Comsoc Communications and Information Security 2019 Technical Recognition Award, the IEEE CS Services Computing 2017 Research Innovation Award, the ACM CODASPY 2017 Lasting Research Award, and the ACM SACMAT 10 Year Test of Time Awards for 2018 and 2019 (for papers published in 2008 and 2009). Her 44+ year career includes industry (Honeywell), federal research laboratory (MITRE), US government (NSF) and US Academia. Her work has resulted in 140+ journal articles, 300+ conference papers, 200+ keynote and featured addresses, seven US patents, sixteen books, and over 120 panel presentations including at Fortune Media, Lloyds of London Insurance, Dell Technologies World, United Nations, and the White House Office of Science and Technology Policy. She has also written opinion columns for popular venues such as the New York Times, Inc. Magazine, Womensday.com and the Legal 500, She received her PhD from the University of Wales, Swansea, UK, and the prestigious earned higher doctorate (D. Eng) from the University of Bristol, UK. She also has a Certificate in Public Policy Analysis from the London School of Economics and Political Science. She has been featured in the book by the ACM in 2024 titled: “Rendering History: The Women of ACM-W” as one of the 30+ “Women that Changed the Face of World Wide Computing Forever.”
Distinguished LERSAIS and Pitt Cyber Seminar
co-hosted by Pitt Cyber
Title: Applying Machine Learning to Securing Cellular Networks
Speaker: Elisa Bertino, Samuel Conte Distinguished Professor of Computer Science at Purdue University, Vice-President ACM; Fellow of IEEE, ACM and AAAS
Time/Venue: Oct 10, 2024
Security is more critical than ever, given the increased complexity of these networks and the numbers of applications that depend on them, including telehealth, remote education, ubiquitous robotics and autonomous vehicles, smart cities, and Industry 4.0. In order to devise more effective defenses, a recent trend is to leverage machine learning (ML) techniques, which have become applicable because of today advanced capabilities for collecting data as well high-performance computing systems for training of ML models. Recent large language models (LLMs) are also opening new interesting directions for security applications. In this talk, I will first present a comprehensive threat analysis in the context of 5G cellular networks to give a concrete example of the magnitude of the problem of cellular network security. Then, I will present two specific applications of ML techniques for the security of cellular networks. The first application focuses on the use of natural language processing techniques to the problem of detecting inconsistencies in the "natural language specifications" of cellular network protocols. The second application addresses the design of an anomaly detection system able to detect the presence of malicious base stations and determine the type of attack. Then I'll conclude with a discussion on research directions.
Bio: Elisa Bertino is a Samuel Conte Distinguished Professor of Computer Science at Purdue University. She serves as Director of the Purdue Cyberspace Security Lab (Cyber2Slab). Prior to joining Purdue, she was a professor and department head at the Department of Computer Science and Communication of the University of Milan. She has been a visiting researcher at the IBM Research Laboratory in San Jose (now Almaden), at Rutgers University, at Telcordia Technologies. She has also held visiting professor positions at the Singapore National University and the Singapore Management University. Her recent research focuses on security and privacy of cellular networks and IoT systems, and on edge analytics for cybersecurity. Elisa Bertino is a Fellow member of IEEE, ACM, and AAAS. She received the 2002 IEEE Computer Society Technical Achievement Award for “For outstanding contributions to database systems and database security and advanced data management systems”, the 2005 IEEE Computer Society Tsutomu Kanai Award for “Pioneering and innovative research contributions to secure distributed systems”, the 2019-2020 ACM Athena Lecturer Award, and the 2021 IEEE 2021 Innovation in Societal Infrastructure Award. She received an Honorary Doctorate from Aalborg University in 2021 and an Honorary Research Doctorate in Computer Science from the University of Salerno in 2023. She is currently serving as ACM Vice-president.