Select a calendar:
Filter October Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for October
-
CS Colloquium: Ali Babar (University of Adelaide) - Building ML Based Software Security Solutions: Data Wrangling Lessons and Recommendations
Mon, Oct 09, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ali Babar, University of Adelaide, Australia
Talk Title: Building ML Based Software Security Solutions: Data Wrangling Lessons and Recommendations
Abstract: Learning based approaches to ensuring software security are attracting significant interest. It is well known that AI and ML based approaches are heavily reliant on the quality of data garbage in, garbage out. Hence, Data Wrangling serves as an important, but expensive, phase of using AI and ML for software security. Like any AI and ML based effort, our R and D efforts for leveraging AI and ML for software security have encountered several significant challenges of Data Wrangling. Our pursuit of finding and devising reliable solutions to security data quality challenges has taught us that the expensiveness and error proneness of Data Wrangling activities can be a barrier to widespread industrial adoption of AI and ML based approaches to software security. We believe that it is important to engage the relevant stakeholders for developing and sharing knowledge and technologies aimed at improving software security data quality. To this end, we are not only systematically identifying and synthesizing the existing empirical literature on improving data quality, but also devising suitable solutions for easing the problems we experienced and observed during Data Wrangling. This talk will draw lessons and recommendations from our efforts of systematically reviewing the state of the art and developing solutions for improving data quality while building and using AI and ML based software security solutions such as SVP models.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: M. Ali Babar is a Professor in the School of Computer Science, University of Adelaide, Australia. He leads a theme on architecture and platform for security as service in Cyber Security Cooperative Research Centre (CSCRC), a large initiative funded by the Australian government, industry, and research institutes. Professor Babar leads one of the largest projects on Software Security in the ANZEC region funded by the CSCRC. Software Security with Focus on Critical Infrastructure, SOCRATES, brings more than 75 researchers and practitioners from 10 organization for developing and evaluating novel knowledge and AI based platforms, methods, and tools for software security. Prof Babar established an interdisciplinary R and D centre called CREST, Centre for Research on Engineering Software Technologies, where he directs the research, development and education activities of more than 30 researchers and engineers in the areas of Software Systems Engineering, Security and Privacy, and Social Computing. Professor Babar obtained a Ph.D. in Computer Science and Engineering from the school of computer science and engineering of University of New South Wales, Australia. He also holds a M.Sc. degree in Computing Sciences from University of Technology, Sydney, Australia
Host: Nenad Medvidovic
Location: Olin Hall of Engineering (OHE) - 100D
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
CS Colloquium: Ralph Lange (Bosch) - From Dexterous Assembly to AMR Fleet Planning: Robotics Research at Bosch
Tue, Oct 10, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ralph Lange, Bosch
Talk Title: From Dexterous Assembly to AMR Fleet Planning: Robotics Research at Bosch
Abstract: The Bosch Group has a uniquely diverse set of robotic products and applications, from consumer, to professional service, to industrial robotics. The research topics in robotics being studied at the various Bosch Research locations around the globe are even broader. In the first part, this talk gives an overview to these topics including SLAM, human motion prediction, and MPC based motion planning for mobile robots, learning and planning for complex assembly tasks with dexterous joining processes, scene segmentation and learning for robot handling in warehouses, novel mechatronic elements for robotic insertion processes in mass production.
The second part covers research on robot software platforms and tools, with many contributions to the open source Robot Operating System. This includes for example micro ROS, execution management, and very new research on methods for model checking of robot deliberation with Behavior Trees. Finally, in the third part, a spotlight on the research on multi agent path finding for AMRs in intralogistics but also for contactless planar systems such as ctrlX FLOW6D is given.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Ralph Lange is head of the global research portfolio for robotics at Bosch. Since 2018, he has been Principal Investigator in three EU funded projects. OFERA (micro ROS), MROS, and CONVINCE. In the last years and in his role as Chief Expert for Robotic Systems and Software Engineering, he has been particularly active in the ROS community and represented Bosch in the ROS 2 Technical Steering Committee and ROS Industrial Europe. Before joining Bosch in 2013, Ralph worked as a software engineer for TRUMPF Machine Tools. He obtained his PhD in computer science from the University of Stuttgart, Germany in 2010.
Host: Sven Koenig
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
CS Colloquium: Michael Safaee (Keck) - From Tethers to Telomeres: Advances in Spine Surgery
Tue, Oct 10, 2023 @ 04:00 PM - 05:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Michael Safaee, Keck Medicine of USC
Talk Title: From Tethers to Telomeres: Advances in Spine Surgery
Abstract: Junctional mechanical failures are a well recognized complication of long segment spinal fusions. Ligament augmentation with tethers can reduce junctional stress and minimize rates of proximal junctional failure PJF. A total of 242 patients with tethers were analyzed and compared to a historical cohort of 77 patients without tethers. Rates of reoperation for PJF were significantly lower with tethers 3.3 percent vs. 15.6 percent, p less than 0.001. A propensity matched cohort of 40 patients in each arm found similarly lower rates of PJF. 2.5 percent vs 22.5 percent, p equals 0.007). PJF emphasizes the need for improved preoperative risk stratification. Telomeres are DNA protein complexes that serve an important role in protecting genomic DNA. Their shortening is a consequence of aging and environmental exposures, with well established associations with diseases of aging and mortality. Whole blood was collected preoperatively on adults undergoing spine surgery. Telomere length analysis was performed using qPCR, T over S ratio. Among 43 patients, we found no significant difference in chronological age, DMI, frailty, or preoperative disability scores when comparing patients with a postoperative complication compared to those without a complication. However, patients with complications had significantly shorter telomere length T over S 0.712 vs. 0.813, p equals 0.008, which correlated to an additional attrition of 9 to 10 years despite only 5 year difference in chronological age. These data suggest that biological age may provide valuable information on preoperative risk and improve current risk calculators.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Michael Safaee, MD, is a neurosurgeon specializing in the treatment of spinal disorders. He is trained in both traditional open and minimally invasive techniques, spinal oncology and adult deformity. While committed to caring for all patients, he has a special interest in scoliosis, kyphosis and revision surgery. Dr. Safaees goal is to treat patients with the same care he would want for his own family, providing safe, effective and durable outcomes tailored to the individual patient. Although surgery is almost always a last resort, he strives to educate patients with the knowledge needed to make the best decision for themselves. Dr. Safaee earned his medical degree from the David Geffen School of Medicine at the University of California, Los Angeles, followed by residency in the Department of Neurological Surgery at the University of California, San Francisco. He completed a fellowship in the Department of Orthopedic Surgery at The Johns Hopkins Hospital. Dr. Safaee has over 100 peer reviewed publications and his work was recognized with the Russell A. Hibbs Award by the Scoliosis Research Society. Dr. Safaees research is currently focused on surgical outcomes in adult deformity surgery and spinal oncology, with a particular interest in risk assessment and data analytics. He is exploring the use of genetic and biological age as components of risk stratification.
Host: Nenad Medvidovic
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
CS Colloquium: Christopher Torng (USC / ECE) - Accelerating Chip-Building Design Cycles for Future Generations of Computing
Tue, Oct 17, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Christopher Torng, USC / ECE
Talk Title: Accelerating Chip-Building Design Cycles for Future Generations of Computing
Series: Computer Science Colloquium
Abstract: The chip building industry is a major cornerstone of the global economy. Unfortunately, it is difficult to produce high-quality designs quickly and at low cost using traditional hardware design flows. This makes it challenging for the community to build new performant and efficient domain-specific accelerators in a timely manner, especially as areas such as machine learning continue to quickly evolve. This talk focuses on new architectures, systems, and design tools to accelerate chip building design cycles for future generations of computing systems. Specifically, we will explore a set of vertically integrated techniques (compiler, architecture, and VLSI) to significantly reduce the design effort to build a coarse-grain reconfigurable array (CGRA) architecture, a flexible architectural template that can be specialized towards many different application domains. I will also introduce an end-to-end agile accelerator-compiler co-designed flow to iteratively evolve such systems across multiple generations of hardware accelerators.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Christopher Torng is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Southern California. Prior to his appointment, he was a postdoctoral researcher at Stanford University from 2019 to 2022 operating in the leadership of the Stanford AHA Agile Hardware Project, where he worked on creating high-performance and energy-efficient architectures for domain-specific hardware acceleration supported by an agile software-hardware co-design methodology. He received his Ph.D. degree from Cornell University in electrical and computer engineering in 2019. He has over ten years of experience building complex digital SoCs as ASIC prototypes as well as new agile flow tools that have already supported tapeouts for at least 12 academic chips, implemented in technologies from 180nm to 12nm. His activities have resulted in his selection as a Rising Star in Computer Architecture (2018) by Georgia Tech as well as an IEEE MICRO Top Pick from Hot Chips (2018).
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Marynel Vazquez (Yale University) - Towards Robots with Increased Social Context Awareness
Thu, Oct 19, 2023 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Marynel Vazquez, Yale University
Talk Title: Towards Robots with Increased Social Context Awareness
Abstract: It is common to study human-robot interactions in well-controlled laboratory environments that vary in limited ways during the encounters. However, many real-world applications require robot adaptation to dynamic interaction scenarios. For example, robots may navigate across different places or interact with different people as they try to complete a task. Fundamental to this adaptation is a robot's ability to reason about their social context. How should we abstract this context in Human-Robot Interaction (HRI)? What models should we use to reason about the many contextual factors that matter to an application of interest? In this talk, I will describe experimental work that highlights the importance of reasoning about different contextual factors in HRI. Then, I will present recent results on leveraging graph abstractions and relational data-driven models to make inferences about the context of interactions and drive robot behavior. Further, because data is generally scarce in HRI, I will also describe two directions to facilitate data collection in Human-Robot Interaction. One direction focuses on creating an open robot platform for studying social interactions in public environments. The other one aims to scale HRI data collection for early system development and testing via online interactive surveys. We have begun to explore the latter idea for social robot navigation but, thanks to advances in game development engines, it could be easily applied to other HRI application domains.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Marynel Vázquez is an Assistant Professor in Yale's Computer Science Department, where she leads the Interactive Machines Group. Her research focuses on Human-Robot Interaction (HRI), especially in multi-party and group settings. Marynel is a recipient of the 2022 NSF CAREER Award, two Amazon Research Awards and a Google Research Scholar Award. Recently, her work has been recognized with best paper awards at HRI'23 and RO-MAN'22. Prior to Yale, Marynel was a Post-Doctoral Scholar at the Stanford Vision & Learning Lab and obtained her M.S. and Ph.D. in Robotics from Carnegie Mellon University, where she was a collaborator of Disney Research. Before then, she received her bachelor's degree in Computer Engineering from Universidad Simón BolÃvar in Caracas, Venezuela.
Host: Stefanos Nikolaidis
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CAIS Webinar: ChatGPT and Large Language Models for Social Work Science: Ethical Challenges, Opportunities, and Next Steps
Thu, Oct 19, 2023 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Aviv Landau, UPenn
Talk Title: ChatGPT and Large Language Models for Social Work Science: Ethical Challenges, Opportunities, and Next Steps
Abstract: Dr. Aviv Landau will discuss and outline the challenges and opportunities that ChatGPT and other large language models pose across bias, legality, ethics, data privacy, confidentiality, informed consent, and academic misconduct. Furthermore, he will talk about initial research in implementing ChatGPT in social work research promoting advocacy.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Aviv Y. Landau is the Co Director of SAFElab and a research assistant professor at UPenns School of Social Policy and Practice. His research focuses on developing and implementing interdisciplinary computational and social work approaches. Landaus main topics of interest are youth health disparities, ethical artificial intelligence, and social media.
Register for the Zoom webinar here: https://usc.zoom.us/webinar/register/WN_Babi0TKrSAKyoZ4tFSI1pQ
Host: CAIS
More Info: https://usc.zoom.us/webinar/register/WN_Babi0TKrSAKyoZ4tFSI1pQ
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/webinar/register/WN_Babi0TKrSAKyoZ4tFSI1pQ
-
CS Colloquium: Michael Pazzani (ISI/USC) - Expert-Informed, User-Centric Explanations for Image Classification with Deep Learning
Thu, Oct 19, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Michael Pazzani, ISI / USC
Talk Title: Expert-Informed, User-Centric Explanations for Image Classification with Deep Learning
Series: Computer Science Colloquium
Abstract: We argue that the dominant approach to explainable AI for explaining image classification with deep learning-“ annotating images with heatmaps, provides little value for users unfamiliar with deep learning. Instead, we argue that explainable AI for images should produce output like experts produce when communicating with one another, with apprentices, and with novices. We discuss a bit of the history of interpretable and explainable AI with examples from AI & medicine. A new approach that labels image regions with diagnostic features is proposed and evaluated. We draw on examples from radiology, ophthalmology, dermatology as well as bird classification.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Michael Pazzani is a Principal Scientist at the Information Sciences Institute at the University of Southern California. Dr. Pazzani was the Vice Chancellor for Research and Economic Development at the University of California, Riverside where he was also a professor of computer science with additional appointments in statistics and psychology. From 2006-2012 he was the Vice President for Research and Economic Development at Rutgers, the State University of New Jersey, where he was also a Distinguished Professor of Computer Science. Prior to his appointment at Rutgers, Dr. Pazzani was the Director of the Information and Intelligent Systems Division at the National Science Foundation. He also served as a member of the Board of Regents of the National Library of Medicine at the National Institutes of Health from 2003- 2005. In 2019, Dr. Pazzani was appointed to the Defense Science Board. Dr. Pazzani started his career as an assistant, associate, and full professor as well as department chair of Information and Computer Science at the University of California, Irvine.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Lerrel Pinto (NYU) - Three Lessons for Building General-Purpose Robots
Fri, Oct 20, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Lerrel Pinto, NYU
Talk Title: Three Lessons for Building General-Purpose Robots
Abstract: Over the last decade, a variety of paradigms have sought to teach robots complex and dexterous behaviors in real world environments. On one end of the spectrum we have nativist approaches that bake in fundamental human knowledge through physics models, simulators and knowledge graphs. While on the other end of the spectrum we have tabula rasa approaches that teach robots from scratch. In this talk I will argue for the need for better constructivist approaches to robotics, i.e. techniques that take guidance from humans while allowing robots to continuously adapt in changing scenarios. The constructivist guide I propose will focus on three lessons. First, creating physical interfaces to allow humans to provide robots with rich and dexterous data. Second, developing adaptive learning mechanisms to allow robots to continually fine tune in their environments. Third, architecting models that allow robots to learn from uncurated play. Applications of such a learning paradigm will be demonstrated on mobile manipulators in home environments, industrial robots on precision tasks, and multifingered hands on dexterous manipulation.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Lerrel Pinto is an Assistant Professor of Computer Science at NYU. His research interests focus on creating general purpose robotic systems. He received a PhD degree from CMU in 2019 prior to that he received an MS degree from CMU in 2016, and a B.Tech in Mechanical Engineering from IIT Guwahati. His work on robotics received paper awards at ICRA 2016 and RSS 2023, and finalist awards at IROS 2019 and CoRL 2022. He is a recipient of grants and awards from Amazon, Honda, Hyundai, Meta, LG and Google. More recently, he was named a TR35 innovator under 35 for 2023. Several of his works have been featured in popular media like TechCrunch, MIT Tech Review, Wired, and BuzzFeed among others. His recent work can be found on www.lerrelpinto.com
Host: Stefanos Nikolaidis
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
AI4Health Center: Cyrus Shahabi (USC) - Privacy-preserving Release of Location Data for Health Applications
Mon, Oct 23, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Cyrus Shahabi, USC
Talk Title: Privacy-preserving Release of Location Data for Health Applications
Series: AI4Health Center
Abstract: In this talk, I will discuss how location data is crucial for various health applications, such as preparing for pandemics, finding early signs of Alzheimer's disease, and measuring human performance. At the same time, I will underscore the sensitivity of this data, exacerbated by growing privacy concerns, potentially hindering its accessibility. Therefore, I will survey various strategies aimed at protecting location privacy, all the while preserving the utility of these applications.
Of particular focus will be our utilization of advanced deep neural network techniques for the release of private aggregated location data and the generation of synthetic location visit sequences. Finally, I'll wrap up by discussing new ways to use location data in the future, along with the open challenges and questions we need to address.
Biography: Cyrus Shahabi is a Professor of Computer Science, Electrical & Computer Engineering, and Spatial Sciences; Helen N. and Emmett H. Jones Professor of Engineering; and the director of the Integrated Media Systems Center (IMSC) at USC. He was also the chair of the Thomas Lord Department of Computer Science at USC from 2017 to 2022. He was co-founder of two USC spin-offs, Geosemble Technologies and Tallygo. He authored two books and more than three hundred research papers in databases, GIS, and multimedia with 14 US Patents. Dr. Shahabi chaired the founding nomination committee of ACM SIGSPATIAL for its first term (2008-2011 term) and served as the chair of ACM SIGSPATIAL for the 2017-2020 term. He was an Associate Editor of IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Knowledge and Data Engineering, and VLDB Journal. He is currently Editor in Chief of PVLDB Vol. 17 (PC Chair of VLDB 2024) and on the editorial board of the ACM Transactions on Spatial Algorithms and Systems and ACM Computers in Entertainment. Dr. Shahabi is a recipient of the ACM Distinguished Scientist award, the U.S. Presidential Early Career Awards for Scientists and Engineers (PECASE), and the NSF CAREER award. He is a fellow of the National Academy of Inventors (NAI) and IEEE.
Host: Michael Pazzani (ISI)
More Info: https://www.isi.edu/events/4218/privacy-preserving-release-of-location-data-for-health-applications/
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
Event Link: https://www.isi.edu/events/4218/privacy-preserving-release-of-location-data-for-health-applications/
-
CAIS Webinar: Beyond Datasets – How the Small Decisions We Make Affect The Tools We Build
Tue, Oct 24, 2023 @ 12:00 PM - 01:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nyalleng Moorosi, Senior Researcher at DAIR
Talk Title: Beyond Datasets -“ How the Small Decisions We Make Affect The Tools We Build
Series: CS Colloquium
Abstract: Data and our understanding of correctness and ground truth are a function of our history, culture and our position in society. In this talk, I wish to share with you some of the often nondocumented decisions we make as builders of machine learning tools and how they challenge the theory of building for all
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Nyalleng Moorosi is a senior researcher at DAIR, and her research interests are in understanding how we can build models which center populations often regarded as peripheral.
Register for the Zoom webinar here: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
Host: CAIS
More Info: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/webinar/register/WN_evMt4EB7S9SVoq0XVzJ1yw
-
CS Colloquium: Feng Qian (USC / ECE) - Towards Robust and Resource-efficient Immersive Content Streaming
Tue, Oct 24, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Feng Qian, USC / ECE
Talk Title: Towards Robust and Resource-efficient Immersive Content Streaming
Series: Computer Science Colloquium
Abstract: Compared to delivering regular 2D videos, streaming immersive content such as 360-degree panoramic videos, volumetric videos, and virtual/mixed reality (VR/MR) content presents distinct challenges due to their intensive network and compute resource consumption. In this talk, I will detail our team's journey over the past five years to boost the robustness, resource efficiency, and user experience of immersive content streaming. Our high-level design principles include adapting to the network & compute resources, integrating viewers' motion patterns, and harnessing the power of AI through edge computing. Backed up with real prototype implementation and field trials, our efforts make it feasible to stream high-quality immersive content to commodity mobile devices such as untethered smartphones and entry-level VR/MR headsets.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Feng Qian is an associate professor in the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering at the University of Southern California. His research interests cover the broad areas of intelligent mobile systems (including 5G/6G), virtual, augmented, and mixed reality (VR/AR/MR) systems, cross-layer system design & analysis, application & transport layer protocols, and real-world system measurement. He obtained his Ph.D. in Computer Science and Engineering from the University of Michigan. He received multiple awards including the AT&T Key Contributor Award, the Google Faculty Award, two ACM CoNEXT best paper awards (2016, 2018), the NSF CAREER Award, the Trustees Teaching Award, the DASH-IF Excellence Award, the Cisco Research Award, the ACM SIGCOMM Best Student Paper Award (2021), the Google Research Scholar Award, two ACM MobiCom best community paper awards (2022, 2023), and the Okawa Research Grant.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
CS Colloquium: Luca Luceri (ISI/USC) - AI-Driven Approaches for Countering Influence Campaigns in Socio-Technical Systems
Thu, Oct 26, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Luca Luceri, ISI / USC
Talk Title: AI-Driven Approaches for Countering Influence Campaigns in Socio-Technical Systems
Abstract: The proliferation of online platforms and social media has sparked a surge in information operations designed to manipulate public opinion on a massive scale, posing significant harm at both the individual and societal levels. In this talk, I will outline a research agenda focused on identifying, investigating, and mitigating orchestrated influence campaigns and deceptive activities within socio-technical systems. I will start by detailing my research efforts in designing AI-based approaches for detecting state-backed troll accounts on social media. Modeling human decision-making as a Markov Decision Process and using an Inverse Reinforcement Learning framework, I will illustrate how we can extract the incentives that social media users respond to and differentiate genuine users from state-sponsored operators. Next, I will delve into a set of innovative approaches I developed to uncover signals of inauthentic, coordinated behaviors. By combining embedding techniques to unveil unexpected similarities in the activity patterns of social media users, along with graph decomposition methods, I will show how we can reveal network structures that pinpoint coordinated groups orchestrating information operations. Through these approaches, I will provide actionable insights to inform regulators in shaping strategies to tame harm, discussing challenges and opportunities to improve the resilience of the information ecosystem, including the potential for interdisciplinary collaborations to address these complex issues.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Luca Luceri is a Research Scientist at the Information Sciences Institute (ISI) at the University of Southern California (USC). His research incorporates machine learning, data and network science, with a primary focus on detecting and mitigating online harms in socio-technical systems. He investigates deceptive and malicious behaviors on social media, with a particular emphasis on problems such as social media manipulation, (mis-)information campaigns, and Internet-mediated radicalization processes. His research advances AI/ML/NLP for social good, computational social science, and human-machine interaction. In his role as a Research Scientist at ISI, Luca Luceri serves as a co-PI of the DARPA-funded program INCAS, aiming to develop techniques to detect, characterize, and track geopolitical influence campaigns. Additionally, he is the PI of a Swiss NSF-sponsored project called CARISMA, which develops network models to simulate the effects of moderation policies to combat online harms.
Host: CS Department
Location: Olin Hall of Engineering (OHE) - 136
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
