5 papers
Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data
Kevin Kasa, Scott C. Lowe, Graham W. Taylor
Set-valued classification (SVC) offers a practical approach to communicating uncertainty while maintaining accuracy by predicting variable-sized sets per input rather than fixed-si…
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspi…
LAST SToP For Modeling Asynchronous Time Series
Shubham Gupta, Thibaut Durand, Graham Taylor +1
We present a novel prompt design for Large Language Models (LLMs) tailored to Asynchronous Time Series. Unlike regular time series, which assume values at evenly spaced time points…
Adapting Prediction Sets to Distribution Shifts Without Labels
Kevin Kasa, Zhiyu Zhang, Heng Yang +1
Recently there has been a surge of interest to deploy confidence set predictions rather than point predictions in machine learning. Unfortunately, the effectiveness of such predict…
Bandit-Driven Batch Selection for Robust Learning under Label Noise
Michal Lisicki, Mihai Nica, Graham W. Taylor
We introduce a novel approach for batch selection in Stochastic Gradient Descent (SGD) training, leveraging combinatorial bandit algorithms. Our methodology focuses on optimizing t…