More Like this

1. Disentangling Influence: Using disentangled representations to audit model predictions

   Charles Marx, Richard Phillips ( January 2019 , Advances in Neural Information Processing Systems, 2019)

   Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence. 

   more » « less
2. Disentangling Influence: Using disentangled representations to audit model predictions

   Marx, Charles ; Phillips, Richard ; Friedler, Sorelle A. ; Scheidegger, Carlos ; Venkatasubramanian, Suresh ( January 2019 , Proceedings of Neural Information Processing Systems (NeurIPS))

   Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence. 

   more » « less
3. The Decisive Power of Indecision: Low-Variance Risk-Limiting Audits and Election Contestation via Marginal Mark Recording

   Fuller, Benjamin ; Pai, Rashmi ; Russell, Alexander ( August 2024 , USENIX Security)

   Risk-limiting audits (RLAs) are the established techniques for verifying large elections. While they provide rigorous guarantees of correctness, widespread adoption has been impeded by both efficiency concerns and the fact they offer statistical, rather than absolute, conclusions. We define new families of audits that help to address these issues. Our new audits are enabled by revisiting the standard notion of a cast-vote record so that it can declare multiple possible mark interpretations rather than a single decision; this can reflect the presence of ambiguous marks, which appear regularly on hand-marked ballots. We show that this simple expedient can offer significant efficiency improvements with only minor changes to existing auditing infrastructure. We establish that these "Bayesian" comparison audits are indeed risk-limiting in the formal sense of (Fuller, Harrison, and Russell, 2022). We then define a new type of post-election audit we call a contested audit. These call for each candidate to provide a cast-vote record table advancing their own claim to victory. We prove that these audits offer remarkable sample efficiency: they guarantee negligible risk with only a constant number of ballot inspections. This is a first for an audit with provable soundness. These results are formulated in a game-based security model that specify quantitative soundness and completeness guarantees. Finally, we observe that these audits provide a direct means to handle contestation of election results affirmed by conventional RLAs. 

   more » « less
4. The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features

   https://doi.org/10.1145/3640543.3645210  

   Goyal, Navita ; Baumler, Connor ; Nguyen, Tin ; Daumé_III, Hal ( March 2024 , ACM)

   AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants’ perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments—explanations, model bias disclosure and proxy correlation disclosure—affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making. 

   more » « less
5. Incentivizing Recourse through Auditing in Strategic Classification

   Estornell, Andrew ; Chen, Yatong ; Das, Sanmay ; Liu, Yang ; Vorobeychik, Yevgeniy ( August 2023 , International Joint Conference on Artificial Intelligence)

   The increasing automation of high-stakes decisions with direct impact on the lives and well-being of individuals raises a number of important considerations. Prominent among these is strategic behavior by individuals hoping to achieve a more desirable outcome. Two forms of such behavior are commonly studied: 1) misreporting of individual attributes, and 2) recourse, or actions that truly change such attributes. The former involves deception, and is inherently undesirable, whereas the latter may well be a desirable goal insofar as it changes true individual qualification. We study misreporting and recourse as strategic choices by individuals within a unified framework. In particular, we propose auditing as a means to incentivize recourse actions over attribute manipulation, and characterize optimal audit policies for two types of principals, utility-maximizing and recourse-maximizing. Additionally, we consider subsidies as an incentive for recourse over manipulation, and show that even a utility-maximizing principal would be willing to devote a considerable amount of audit budget to providing such subsidies. Finally, we consider the problem of optimizing fines for failed audits, and bound the total cost incurred by the population as a result of audits. 

   more » « less