Fairness and Robustness in Machine Learning

Identifier:  TDX:4000

Handle: https://hdl.handle.net/20.500.11797/TDX4000

Authors:  Khandpur Singh, Ashneet

Abstract:
Machine learning models learn from data to model concrete environments and problems and predict future events but, if the data are biased, they may reach biased conclusions. Therefore, it is critical to make sure their predictions are fair and not based on discrimination against specific groups or communities. Federated learning, a type of distributed machine learning, needs to be equipped with techniques to tackle this grand and interdisciplinary challenge. Even if FL provides stronger privacy guarantees to the participating clients than centralized learning, it is vulnerable to some attacks whereby malicious clients submit bad updates in order to prevent the model from converging or, more subtly, to introduce artificial biases in the models' predictions or decisions (poisoning). A downside of anti-poisoning techniques is that they might lead to discriminating against minority groups whose data are significantly and legitimately different from those of the majority of clients. In this work, we strive to strike a balance between fighting poisoning and accommodating diversity to help learn fairer and less discriminatory federated learning models. In this way, we forestall the exclusion of diverse clients while still ensuring the detection of poisoning attacks. On the other hand, in order to develop fair models and verify the fairness of these models in the area of machine learning, we propose a method, based on counterfactual examples, that detects any bias in the ML model, regardless of the data type used in the model.