13 citations · 33 across the 15 of their papers we have counts for
15 papers
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…
Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics
Carlos Mougan, Joshua Brand
Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequence…
How to Data in Datathons
Carlos Mougan, Richard Plant, Clare Teng +7
The rise of datathons, also known as data or data science hackathons, has provided a platform to collaborate, learn, and innovate in a short timeframe. Despite their significant po…
AI and the EU Digital Markets Act: Addressing the Risks of Bigness in Generative AI
Ayse Gizem Yasar, Andrew Chong, Evan Dong +9
As AI technology advances rapidly, concerns over the risks of bigness in digital markets are also growing. The EU's Digital Markets Act (DMA) aims to address these risks. Still, th…
The Role of Large Language Models in the Recognition of Territorial Sovereignty: An Analysis of the Construction of Legitimacy
Francisco Castillo-Eslava, Carlos Mougan, Alejandro Romero-Reche +1
We examine the potential impact of Large Language Models (LLM) on the recognition of territorial sovereignty and its legitimization. We argue that while technology tools, such as G…
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…
Explanation Shift: Detecting distribution shifts on tabular data via the explanation space
Carlos Mougan, Klaus Broelemann, Gjergji Kasneci +2
As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator…
Introducing explainable supervised machine learning into interactive feedback loops for statistical production system
Carlos Mougan, George Kanellos, Johannes Micheler +2
Statistical production systems cover multiple steps from the collection, aggregation, and integration of data to tasks like data quality assurance and dissemination. While the cont…
Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap
Carlos Mougan, Dan Saattrup Nielsen
Monitoring machine learning models once they are deployed is challenging. It is even more challenging to decide when to retrain models in real-case scenarios when labeled data is b…
Fairness Implications of Encoding Protected Categorical Attributes
Carlos Mougan, Jose M. Alvarez, Salvatore Ruggieri +1
Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, howeve…
Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems
Carlos Mougan, David Masip, Jordi Nin +1
Regression problems have been widely studied in machinelearning literature resulting in a plethora of regression models and performance measures. However, there are few techniques…