Select a calendar:
Filter November Events by Event Type:
Events for November 09, 2023
-
NL Seminar - Manipulating Large Language Model Predictions Through Data
Thu, Nov 09, 2023 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Alexander Wan, University of Cal-Berkeley
Talk Title: Manipulating Large Language Model Predictions Through Data
Series: NL Seminar
Abstract: This talk will be a live presentation only, it will not be recorded.
REMINDER: Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you are highly encouraged to use your USC account to sign into Zoom.
If you’re an outside visitor, please provide your: Full Name, Title and Name of Workplace to (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance. Also, let us know if you plan to attend in-person or virtually.
More Info on NL Seminars can be found at: https://nlg.isi.edu/nl-seminar/
Large language models use large amounts of unmoderated data at each stage of the training and deployment pipeline. In this talk, I will show how these lax requirements enable adversaries to manipulate both training and test data, allowing a myriad of possible attacks. First, during training time, I will show that adversaries can modify instruction-tuning datasets to systematically manipulate predictions across a range of tasks or induce degenerate outputs across hundreds of arbitrary tasks, using as few as 100 poison examples. At inference time, additional data is often used in retrieval- or tool-augmented models. Naturally, these models will face information from a wide variety of sources that have varying degrees of quality. Humans are also faced with this same range of sources but can make judgements of trustworthiness based on factors like the style of argumentation or the recency of information. We show that not only do model predictions differ significantly from human credibility judgements, but also that gaps in this judgement creates opportunities for adversaries to manipulate answers to user queries.
Biography: Alexander Wan is a third-year undergraduate at UC Berkeley majoring in Computer Science, Statistics, and Mathematics. He works closely with folks at the Berkeley NLP Group and the MSU Heterogeneous Learning and Reasoning lab, with a focus on improving the robustness and interpretability of large language models. He's also more broadly interested in the intersection of machine learning and cognitive science: using current ML models to better understand human cognition and building more robust models through cognitively inspired architectures and training.
Host: Jon May and Justin Cho
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://usc.zoom.us/j/95174101995Location: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://usc.zoom.us/j/95174101995
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
CAIS Webinar: A Carative Approach to AI Governance
Thu, Nov 09, 2023 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Kush R. Varshney, IBM Research
Talk Title: A Carative Approach to AI Governance
Abstract: In recent times, we often hear a call for the governance of AI systems, but what does that really mean? In this talk, I will first adopt a control theory perspective to explain governance that determines the reference input via value alignment, data scientists acting as the controller to meet the values in a machine learning system, and facts captured in transparent documentation as the feedback signal. I will then adopt a nursing theory perspective to explain how the control theory perspective lacks caring and the need for a carative approach that starts with the real world problem as experienced by the most vulnerable people. I will conclude with an example of a project on using machine learning to evaluate applicants for home solar panel systems in rural India.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Kush R. Varshney is a distinguished research scientist and senior manager at IBM Research -“ T. J. Watson Research Center where he leads the Trustworthy Machine Intelligence department and the IBM Science for Social Good initiative
Register for the Zoom webinar here: https://usc.zoom.us/webinar/register/WN_p39kMQKnTaKdaJRKNox5uQ
Host: CAIS
More Info: https://usc.zoom.us/webinar/register/WN_p39kMQKnTaKdaJRKNox5uQ
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/webinar/register/WN_p39kMQKnTaKdaJRKNox5uQ
-
Civil and Environmental Department Seminar Series
Thu, Nov 09, 2023 @ 02:00 PM - 03:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Prof. Babak Moaveni, Tufts University
Talk Title: Digital Twinning of Offshore Wind Turbines Using Vibration Measurements
Host: Dr. Audrey Olivier
More Info: https://usc.zoom.us/j/91558672174
Location: Zoom Only
Audiences: Everyone Is Invited
Contact: Salina Palacios
Event Link: https://usc.zoom.us/j/91558672174
-
Civil and Environmental Department Seminar Series
Thu, Nov 09, 2023 @ 02:00 PM - 03:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Prof. Babak Moaveni, Tufts University
Talk Title: Digital Twinning of Offshore Wind Turbines Using Vibration Measurements
Abstract: See attached abstract
Host: Dr. Audrey Olivier
More Info: https://usc.zoom.us/j/91558672174
More Information: Babak Moaveni Announcement 110923.docx
Location: Zoom Only
Audiences: Everyone Is Invited
Contact: Salina Palacios
Event Link: https://usc.zoom.us/j/91558672174
-
DREAM Industry Mentorship speaker series- Special Session
Thu, Nov 09, 2023 @ 05:00 PM - 07:00 PM
USC Viterbi School of Engineering
University Calendar
DREAM (Direct Response to Engineers Aspirations from Mentors) connects students with high profile industry professionals from a variety of tech and destination companies who help them create a vision for their futures, align their careers around purpose, and build character in the context of growth, reinvention, and constant change. Industry mentors discuss how professional challenges present opportunities for character and leadership development.
This event features Kailash Tulsi Gajara, distinguished Viterbi alumnus and Founder @ Atulsia Technologies and Megastores about his remarkable career as a founder, CEO, entrepreneur and leader in the global technology space.Location: Ronald Tutor Hall of Engineering (RTH) - 217
Audiences: Everyone Is Invited
Contact: Elisabeth Arnold Weiss
Event Link: https://cglink.me/2nB/r393278
-
Leetcode Jam Night #2
.png)
Thu, Nov 09, 2023 @ 05:00 PM - 07:00 PM
Viterbi School of Engineering Student Affairs
Student Activity
Jam with the Viterbi Learning Program! Join us for a company-specific (MAANG) problems session where we code and discuss. Also - we have pizza.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Alex Bronz
Event Link: https://engage.usc.edu/VLP/rsvp_boot?id=393490
-
Intro to CAD & Slicing Software Hands-On Workshop
Thu, Nov 09, 2023 @ 07:00 PM - 08:00 PM
USC Viterbi School of Engineering
Workshops & Infosessions
Join us for a hands-on on workshop with 3D4E, USC's premier 3D printing club! Get an introduction to CAD and slicing software and try out the 3d printers yourself!
Location: Sign into EngageSC to View Location
Audiences: Everyone Is Invited
Contact: Thelma Federico Zaragoza
Event Link: https://engage.usc.edu/WIE/rsvp?id=393346
.png)