Embedded Files
Breaking Machine Learning Models with Adversarial Attacks and its Variants
Wednesay, May 21st 2025, 9:00-10:00am
Room: Grand Ballroom
Supratik Mukhopadhyay
ProfessorDepartment of Environmental SciencesLouisiana State UniversityAbstract: In spite of advances in vaccines and antibiotics, a tremendous amount of research effort has been invested in the recent years for discovering drugs for diseases without a known cure. Millions of people globally suffer from health conditions that necessitate the development of new and more effective treatments. The widespread and prolonged use of antibiotics has led to drug-resistant infections, making current treatments less effective. While antibiotic resistance is increasing rapidly, the development of new antibacterial drugs has slowed to an all-time low. This highlights the urgent need for novel methods to discover new antimicrobial agents. However, traditional drug development techniques are slow, inefficient, and expensive. To address these challenges, we have developed Deep Drug, an AI-powered drug design pipeline that can interpret vast datasets to identify potential new therapeutics. This technology can significantly accelerate drug discovery, reducing both development time and costs.
Climate change and global warming are today recognized as problems that threaten the very existence of humanity on earth. In the recent years, human civilization has been threatened by natural disasters - hurricanes, tornadoes, rise in sea level, droughts, floods, desertification of land, erosion of coastal areas, wildfires, etc. Human activity has resulted in water and air pollution that is adversely affecting population health. Encroachment of humans in animal habitat have threatened biodiversity and ecological balance and have increased the possibility of transmission of diseases from wildlife to humans leading to possible pandemics/epidemics. Environmental disasters have diminished agricultural productivity and led to proliferation of pests, lack of grazing land resulting in reduced animal husbandry, causing increased poverty and reduced food security.
We show how AI can help in tackling the environmental challenges mentioned above through information gathering, processing and analyzing, decision making, observing consequences, and feeding back for forecasting. We discuss our recent work in using AI/ML for carbon mapping, hypoxia predictions, climate smart agriculture, wildfire prediction and detection, preserving biodiversity, and energy efficiency in built environment.
Bio: Supratik Mukhopadhyay is full Professor at Louisiana State University (LSU) at the Center for Computation and Technology and a Data Science Fellow at the Office of Data and Strategic Analytics. Prof. Mukhopadhyay led the DeepDrug team for automated drug discovery using Artificial Intelligence to semifinalist standing in the prestigious AI XPRIZE competition (among 147 teams worldwide), the world's top competition for using AI for solving moonshot challenges. Combination therapy discovered by the DeepDrug Artificial Intelligence Platform for COVID-19 progressed to human trials at the Riverside University Health System, California.
Apart from Drug Discovery, Prof. Mukhopadhyay has worked on AI for agriculture, education, port and supply chain security, satellite image understanding, video and image analytics, design of intelligent buildings and transportation systems, wildfire prediction and detection, conservation of endangered species, intelligent cyber-physical-human systems, etc. His DeepSat framework for satellite imagery understanding influenced NASA Earth Exchange. In the last 16 years, Prof. Mukhopadhyay has garnered more than $9 million in research grants. His research has been funded by the NSF, DARPA, ARO, ONR, NGA, NASA, DOE, USDOT, NRL, USDA, state agencies, nonprofit foundations, and private industry. Prof. Mukhopadhyay has published around 135 refereed publications in reputed journals and conferences. He has been awarded 4 US Patents and has 8 US patents pending. He has received numerous awards for his research. He cofounded a startup Ailectric for commercializing his research on sound, video, and image analytics. He serves as an associate editor for IEEE Transactions on Artificial Intelligence and Remote Sensing letters and has served in the program committees of AAAI.
Climate change and global warming are today recognized as problems that threaten the very existence of humanity on earth. In the recent years, human civilization has been threatened by natural disasters - hurricanes, tornadoes, rise in sea level, droughts, floods, desertification of land, erosion of coastal areas, wildfires, etc. Human activity has resulted in water and air pollution that is adversely affecting population health. Encroachment of humans in animal habitat have threatened biodiversity and ecological balance and have increased the possibility of transmission of diseases from wildlife to humans leading to possible pandemics/epidemics. Environmental disasters have diminished agricultural productivity and led to proliferation of pests, lack of grazing land resulting in reduced animal husbandry, causing increased poverty and reduced food security.
We show how AI can help in tackling the environmental challenges mentioned above through information gathering, processing and analyzing, decision making, observing consequences, and feeding back for forecasting. We discuss our recent work in using AI/ML for carbon mapping, hypoxia predictions, climate smart agriculture, wildfire prediction and detection, preserving biodiversity, and energy efficiency in built environment.
Bio: Supratik Mukhopadhyay is full Professor at Louisiana State University (LSU) at the Center for Computation and Technology and a Data Science Fellow at the Office of Data and Strategic Analytics. Prof. Mukhopadhyay led the DeepDrug team for automated drug discovery using Artificial Intelligence to semifinalist standing in the prestigious AI XPRIZE competition (among 147 teams worldwide), the world's top competition for using AI for solving moonshot challenges. Combination therapy discovered by the DeepDrug Artificial Intelligence Platform for COVID-19 progressed to human trials at the Riverside University Health System, California.
Apart from Drug Discovery, Prof. Mukhopadhyay has worked on AI for agriculture, education, port and supply chain security, satellite image understanding, video and image analytics, design of intelligent buildings and transportation systems, wildfire prediction and detection, conservation of endangered species, intelligent cyber-physical-human systems, etc. His DeepSat framework for satellite imagery understanding influenced NASA Earth Exchange. In the last 16 years, Prof. Mukhopadhyay has garnered more than $9 million in research grants. His research has been funded by the NSF, DARPA, ARO, ONR, NGA, NASA, DOE, USDOT, NRL, USDA, state agencies, nonprofit foundations, and private industry. Prof. Mukhopadhyay has published around 135 refereed publications in reputed journals and conferences. He has been awarded 4 US Patents and has 8 US patents pending. He has received numerous awards for his research. He cofounded a startup Ailectric for commercializing his research on sound, video, and image analytics. He serves as an associate editor for IEEE Transactions on Artificial Intelligence and Remote Sensing letters and has served in the program committees of AAAI.
Choosing the Right Metrics: A Study of Performance Measurement for Binary Classification in Imbalanced and Big Data
Thursday, May 22nd, 2025, 9:00-10:00am
Room: Grand Ballroom
Motorola ProfessorDepartment of Electrical Engineering and Computer Science Florida Atlantic University
Abstract: Predictive modeling with class-imbalanced data has proven to be a challenging task. This problem is well studied, but the era of big data is producing extreme levels of imbalance that are increasingly difficult to model. In addition to the modeling challenges that are associated with these highly imbalanced data sets, we have found that performance evaluation also requires careful considerations. In this talk, we demonstrate how the popular area under the receiver operating characteristic curve can provide misleading results and recommend that any evaluation of imbalanced big data also includes the area under the precision-recall curve.
Bio: Dr. Taghi M. Khoshgoftaar is Motorola Endowed Chair professor of the Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University and the Director of NSF Big Data Training and Research Laboratory. His research interests are in big data analytics, data mining and machine learning, health informatics and bioinformatics, social network mining, security analytics, fraud detection, and software engineering. He has published more than 900 refereed journal and conference papers in these areas. He is the conference chair of the IEEE International Conference on Machine Learning and Applications (ICMLA 2025). He is the Co-Editor-in Chief of the journal of Big Data. He has served on organizing and technical program committees of various international conferences, symposia, and workshops. Also, he has served as North American Editor of the Software Quality Journal and was on the editorial boards of the journals Multimedia Tools and Applications, Knowledge and Information Systems, and Empirical Software Engineering, Software Engineering and Knowledge Engineering, and Social Network Analysis and Mining. For my selected publications, please see my Google Scholar link.
Bio: Dr. Taghi M. Khoshgoftaar is Motorola Endowed Chair professor of the Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University and the Director of NSF Big Data Training and Research Laboratory. His research interests are in big data analytics, data mining and machine learning, health informatics and bioinformatics, social network mining, security analytics, fraud detection, and software engineering. He has published more than 900 refereed journal and conference papers in these areas. He is the conference chair of the IEEE International Conference on Machine Learning and Applications (ICMLA 2025). He is the Co-Editor-in Chief of the journal of Big Data. He has served on organizing and technical program committees of various international conferences, symposia, and workshops. Also, he has served as North American Editor of the Software Quality Journal and was on the editorial boards of the journals Multimedia Tools and Applications, Knowledge and Information Systems, and Empirical Software Engineering, Software Engineering and Knowledge Engineering, and Social Network Analysis and Mining. For my selected publications, please see my Google Scholar link.
Social Science and Social AI: Developing Artificial Social Intelligence to Support Teams
Friday, May 23rd, 2025, 9:00-10:00am
Room: Grand Ballroom
Stephen Fiore
DirectorCognitive Sciences LabUniversity of Central FloridaAbstract: Advances in artificial intelligence (AI) can benefit from a closer integration of concepts and theories in the social and cognitive sciences. I provide an overview of a body of research in social cognition and its relation to developing artificial social intelligence. In the rapidly evolving landscape of AI, such collaborations are needed to advance our understanding of the development of systems that can work alongside with humans as actual teammates. Effective teamwork is crucial in fields that have high-stakes and can require complex collaborative problem solving. In these environments, the ability of team members to collaborate requires social-cognitive processes over and above an understanding of the tasks to be accomplished. We address this through the study of socially intelligent AI and how these influence interactions with human counterparts acting as a team. I first provide an overview of our approach to social cognition and the theoretical concepts being studied. I then describe theory and data from our various research projects studying human-machine teaming. I conclude with recommendations and guidance for future research on artificial social intelligence.
Bio: Dr. Stephen M. Fiore is Director, Cognitive Sciences Laboratory, and Pegasus Professor with the University of Central Florida’s Cognitive Sciences Program in the Department of Philosophy and Institute for Simulation and Training. He maintains a multidisciplinary research interest that incorporates aspects of the cognitive, social, organizational, and computational sciences in the investigation of learning and performance in individuals and teams. His primary area of research is the interdisciplinary study of complex collaborative cognition and the understanding of how humans interact socially and with technology. Most recently, this includes examining aspects of human-AI teaming and how team and task factors relate to process and performance differences. In 2018, Dr. Fiore was nominated to DARPA's Information Sciences and Technology (ISAT) Study Group to help the DoD examine future areas of technological development potentially influencing national security. He has been a visiting scholar for the study of shared and extended cognition at École Normale Supérieure de Lyon in Lyon, France (2010) and an invited visitor to the internationally renowned interdisciplinary Santa Fe Institute (2013). He was also selected to be a member of the expert panel for the Organisation for Economic Co-operation and Development’s 2015 Programme for International Student Assessment (PISA) which focused on collaborative problem-solving skills. He has edited scientific volumes on cognition and collaboration and co-authored over 250 scholarly publications in the area of learning, memory, and problem solving in individuals and groups.
Bio: Dr. Stephen M. Fiore is Director, Cognitive Sciences Laboratory, and Pegasus Professor with the University of Central Florida’s Cognitive Sciences Program in the Department of Philosophy and Institute for Simulation and Training. He maintains a multidisciplinary research interest that incorporates aspects of the cognitive, social, organizational, and computational sciences in the investigation of learning and performance in individuals and teams. His primary area of research is the interdisciplinary study of complex collaborative cognition and the understanding of how humans interact socially and with technology. Most recently, this includes examining aspects of human-AI teaming and how team and task factors relate to process and performance differences. In 2018, Dr. Fiore was nominated to DARPA's Information Sciences and Technology (ISAT) Study Group to help the DoD examine future areas of technological development potentially influencing national security. He has been a visiting scholar for the study of shared and extended cognition at École Normale Supérieure de Lyon in Lyon, France (2010) and an invited visitor to the internationally renowned interdisciplinary Santa Fe Institute (2013). He was also selected to be a member of the expert panel for the Organisation for Economic Co-operation and Development’s 2015 Programme for International Student Assessment (PISA) which focused on collaborative problem-solving skills. He has edited scientific volumes on cognition and collaboration and co-authored over 250 scholarly publications in the area of learning, memory, and problem solving in individuals and groups.
Special Track Invited Speaker:
Special Track Invited Speaker:
Applied Natural Language Processing
Online Community Modeling and Moderation
Wednesday, May 21st 2025, 1:30-2:30pm
Room: Grand Salon 4
Richard Khoury
Associate ProfessorDepartment of Computer Science and Software EngineeringUniversité LavalAbstract: Today, over 5 billion people interact with each other in online communities, ranging from social networking sites to web forums, from video game chats to website comment sections. In most cases these communities eanble participants to connect and communicate with each other in healthy ways – sharing, learning, and befriending each other. Unfortunately, some of these interactions become harmful, and devolve into virulent fights, trolling, cyberbullying, and worse. The most common methods for dealing with harmful messages are through human moderators, keyword filters, and user reports, but these methods all have inherent limitations. In this talk, we will explore how new AI tools, such as community modeling and predictive moderation, can be developed to keep online communities safe and healthy.
Bio: Richard Khoury received his Bachelor’s Degree and his Master’s Degree in Electrical and Computer Engineering from Laval University (Québec City, QC) in 2002 and 2004 respectively, and his Doctorate in Electrical and Computer Engineering from the University of Waterloo (Waterloo, ON) in 2007. From 2008 to 2016, he worked as a faculty member in the Department of Software Engineering at Lakehead University. In 2016, he moved to Université Laval as an associate professor. From 2021 to 2023, he also served as president of the Canadian Artificial Intelligence Association. Dr. Khoury’s primary areas of research are data mining and natural language processing, and additional interests include knowledge management, machine learning, and artificial intelligence.
Bio: Richard Khoury received his Bachelor’s Degree and his Master’s Degree in Electrical and Computer Engineering from Laval University (Québec City, QC) in 2002 and 2004 respectively, and his Doctorate in Electrical and Computer Engineering from the University of Waterloo (Waterloo, ON) in 2007. From 2008 to 2016, he worked as a faculty member in the Department of Software Engineering at Lakehead University. In 2016, he moved to Université Laval as an associate professor. From 2021 to 2023, he also served as president of the Canadian Artificial Intelligence Association. Dr. Khoury’s primary areas of research are data mining and natural language processing, and additional interests include knowledge management, machine learning, and artificial intelligence.
Google Sites
Report abuse