Trustworthy Machine Learning under Social and Adversarial Data Sources

TL;DR

This paper discusses the challenges faced by machine learning systems due to social and adversarial behaviors, emphasizing the need for trustworthy approaches in real-world, strategic, and potentially malicious data environments.

Contribution

It provides a comprehensive overview of the issues and proposes frameworks for developing trustworthy machine learning under social and adversarial data sources.

Findings

Adversarial attacks can significantly degrade ML model performance.

Strategic data sources influence the reliability of machine learning outputs.

Trustworthy ML requires new methods to handle social and adversarial behaviors.

Abstract

Machine learning has witnessed remarkable breakthroughs in recent years. As machine learning permeates various aspects of daily life, individuals and organizations increasingly interact with these systems, exhibiting a wide range of social and adversarial behaviors. These behaviors may have a notable impact on the behavior and performance of machine learning systems. Specifically, during these interactions, data may be generated by strategic individuals, collected by self-interested data collectors, possibly poisoned by adversarial attackers, and used to create predictors, models, and policies satisfying multiple objectives. As a result, the machine learning systems' outputs might degrade, such as the susceptibility of deep neural networks to adversarial examples (Shafahi et al., 2018; Szegedy et al., 2013) and the diminished performance of classic algorithms in the presence of strategic individuals (Ahmadi et al., 2021). Addressing these challenges is imperative for the success of machine learning in societal settings.