13 citations · 33 across the 14 of their papers we have counts for
11 papers · 1 filter
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…
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…
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…
Model Agnostic Explainable Selective Regression via Uncertainty Estimation
Andrea Pugnana, Carlos Mougan, Dan Saattrup Nielsen
With the wide adoption of machine learning techniques, requirements have evolved beyond sheer high performance, often requiring models to be trustworthy. A common approach to incre…
Explanation Shift: How Did the Distribution Shift Impact the Model?
Carlos Mougan, Klaus Broelemann, David Masip +3
As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In practice, new input data tend to come without target labels. Then…
Beyond Demographic Parity: Redefining Equal Treatment
Carlos Mougan, Laura State, Antonio Ferrara +2
Liberalism-oriented political philosophy reasons that all individuals should be treated equally independently of their protected characteristics. Related work in machine learning h…