TrustML Workshop @ UBC, February 2024

February 28, 2024, 9:30 am to 5:00 pm

KAIS 2020/2030

Overview Registration Speakers Call for Briefings/Posters Program
Organizers Pictures from the Event

Overview

The in-person TrustML Workshop @ UBC, organized jointly by the UBC TrustML Research Excellence Cluster and CAIDA, brings together leading researchers and practitioners interested in building trustworthy machine learning systems: systems that are reliable, secure, explainable, and ethical. This workshop features invited talks, tech briefings, poster sessions, and other discussion and networking opportunities with the research community in this field.

Location: Fried Kaiser (KAIS) building, Room 2020/2030, 2332 Main Mall, UBC Vancouver campus (the nearest parkade is the UBC Health Sciences Parkade)

Register Now

Registration deadline: February 21, 2024

Speakers

Call for Tech Briefings and Posters

The TrustML Workshop @ UBC is accepting technical briefing submissions, for 10 to 15 minutes talks, as well as poster submissions. To submit a briefing, a poster, or both, please fill out the form below and include a title and a short description of your work. The submissions will be evaluated based on their relevance to the workshop theme. Don't miss the chance to showcase your research and connect with like-minded individuals at the TrustML Workshop @ UBC!

Important Dates:
~~Submission deadline: February 12, 2024~~
~~Acceptance notifications: February 18, 2024~~

Submit Your Briefing/Poster Proposal Today

Accepted Briefings

Workshop Program

*Pacific Standard Time (US & Canada)

Time	Session
9:00	Registration Opens
9:30-9:50	Welcome, Breakfast, and Mingling
9:50-10:00	Introductions and Poster Briefings (Chair: Julia Rubin)
10:00-11:20	Session 1 (Chair: Mathias Lécuyer) Bryan Wilder, Carnegie Mellon University: "Machine Learning for Public Health Decision Making" Han Yu, Nanyang Technological University: "Towards Personalized Federated Learning"
11:20-12:00	Break, Posters
12:00-13:00	Session 2: Tech Briefings (Chair: Simon Oya) Pierre Tholoniat, Columbia University: "Turbo: Effective Caching in Differentially-Private Databases" Gargi Mitra, The University of British Columbia: "Security Risks in AI/ML-enabled Connected Healthcare Systems" Hooman Vaseli, The University of British Columbia: "ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography" Abraham Chan, The University of British Columbia: "Harnessing Explainability to Improve ML Ensemble Resilience"
13:00-14:00	Lunch, Posters
14:00-15:00	Session 3: Tech Briefings (Chair: Karthik Pattabiraman) Asim Munawar, IBM Research: "Reasoning with LLMs" Weina Jin, Simon Fraser University: "Constructing a Different Imagination Beyond "Outperforming Humans"" Paul Bucci, The University of British Columbia: "Teleoscope: Exploring Themes in Large Document Sets By Example" Manish Nagireddy, IBM Research: "SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models"
15:00-15:30	Break, Posters
15:30-16:50	Session 4 (Chair: Xiaoxiao Li) Lujo Bauer, Carnegie Mellon University: "From Pandas and Gibbons to Malware Detection: Attacking and Defending Real-world Uses of Machine Learning" Sébastien Gambs, Université du Québec à Montréal: "Understanding and Addressing Fairwashing in Machine Learning"
16:50-17:00	Summary and Closing

Accepted Posters

Katharina Beckh, Fraunhofer Institute for Intelligent Analysis and Information Systems: "An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning"
Mohammed Elnwawy, The University of British Columbia: "Risk Profiling Framework for Attacks on ML in Safety-Critical Applications"
Mohammadreza Hallajiyan, The University of British Columbia: "Systematic Security Assessment of AI/ML-Enabled Medical Devices"
Mishaal Kazmi, The University of British Columbia: "PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining"
Nathan Lawrence, The University of British Columbia: "Stability-by-design for Industrial Reinforcement Learning"
Gargi Mitra, The University of British Columbia: "Security Risks in AI/ML-enabled Connected Healthcare Systems"
Asim Munawar, IBM Research: "Reasoning with LLMs"
Manish Nagireddy, IBM Research: "SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models"
Whitney Nelson, University of Texas Austin: "Designing LLM-Based Support for Homelessness Caseworkers"
Nikhil Pratap Ghanathe, The University of British Columbia: "QUTE: Quantifying Uncertainty in TinyML Models with Early-exit-assisted Ensembles"
Shadab Shaikh, The University of British Columbia: "Adaptive Randomized Smoothing: Certifying Multi-Step Defences against Adversarial Examples"
Qiaoyue Tang, The University of British Columbia: "DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)"
Michael Tegegn, The University of British Columbia: "It Is All About Data: The Effects of Data on Adversarial Robustness"
Pierre Tholoniat, Columbia University: "Turbo: Effective Caching in Differentially-Private Databases"
Hooman Vaseli, The University of British Columbia: "ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography"
Jingyi Wang, The University of British Columbia: "Adaptive Digital Twin Identification with Control: An Extended Kalman Filter-based Sparse Nonlinear Identification Approach"