3 papers
cs.LG2025
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
cs.LG2025
Model Monitoring in the Absence of Labeled Data via Feature Attributions Distributions
Carlos Mougan
Model monitoring involves analyzing AI algorithms once they have been deployed and detecting changes in their behaviour. This thesis explores machine learning model monitoring ML b…
cs.LG2025
Measuring Fairness in Financial Transaction Machine Learning Models
Deniz Sezin Ayvaz, Lorenzo Belenguer, Hankun He +12
Mastercard, a global leader in financial services, develops and deploys machine learning models aimed at optimizing card usage and preventing attrition through advanced predictive…