SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning

Machine learning techniques are increasingly used for high-stakes decision-making, such as college admissions, loan attribution or recidivism prediction. Thus, it is crucial to ensure that the models learnt can be audited or understood by human users, do not create or reproduce discrimination or bias, and do not leak sensitive information regarding their training data. Indeed, interpretability, fairness and privacy are key requirements for the development of responsible machine learning, and all three have been studied extensively during the last decade. However, they were mainly considered in isolation, while in practice they interplay with each other, either positively or negatively. In this Systematization of Knowledge (SoK) paper, we survey the literature on the interactions between these three desiderata. More precisely, for each pairwise interaction, we summarize the identified synergies and tensions. These findings highlight several fundamental theoretical and empirical conflicts, while also demonstrating that jointly considering these different requirements is challenging when one aims at preserving a high level of utility. To solve this issue, we also discuss possible conciliation mechanisms, showing that a careful design can enable to successfully handle these different concerns in practice.

Probabilistic Dataset Reconstruction from Interpretable Models

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such disclosure may directly conflict with privacy, a precise quantification of the privacy impact of such breach is a fundamental problem. For instance, previous work have shown that the structure of a decision tree can be leveraged to build a probabilistic reconstruction of its training dataset, with the uncertainty of the reconstruction being a relevant metric for the information leak. In this paper, we propose of a novel framework generalizing these probabilistic reconstructions in the sense that it can handle other forms of interpretable models and more generic types of knowledge. In addition, we demonstrate that under realistic assumptions regarding the interpretable models' structure, the uncertainty of the reconstruction can be computed efficiently. Finally, we illustrate the applicability of our approach on both decision trees and rule lists, by comparing the theoretical information leak associated to either exact or heuristic learning algorithms. Our results suggest that optimal interpretable models are often more compact and leak less information regarding their training data than greedily-built ones, for a given accuracy level.

Fairness Under Demographic Scarce Regime

Most existing works on fairness assume the model has full access to demographic information. However, there exist scenarios where demographic information is partially available because a record was not maintained throughout data collection or due to privacy reasons. This setting is known as demographic scarce regime. Prior research have shown that training an attribute classifier to replace the missing sensitive attributes (proxy) can still improve fairness. However, the use of proxy-sensitive attributes worsens fairness-accuracy trade-offs compared to true sensitive attributes. To address this limitation, we propose a framework to build attribute classifiers that achieve better fairness-accuracy trade-offs. Our method introduces uncertainty awareness in the attribute classifier and enforces fairness on samples with demographic information inferred with the lowest uncertainty. We show empirically that enforcing fairness constraints on samples with uncertain sensitive attributes is detrimental to fairness and accuracy. Our experiments on two datasets showed that the proposed framework yields models with significantly better fairness-accuracy trade-offs compared to classic attribute classifiers. Surprisingly, our framework outperforms models trained with constraints on the true sensitive attributes.

Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods

A hybrid model involves the cooperation of an interpretable model and a complex black box. At inference, any input of the hybrid model is assigned to either its interpretable or complex component based on a gating mechanism. The advantages of such models over classical ones are two-fold: 1) They grant users precise control over the level of transparency of the system and 2) They can potentially perform better than a standalone black box since redirecting some of the inputs to an interpretable model implicitly acts as regularization. Still, despite their high potential, hybrid models remain under-studied in the interpretability/explainability literature. In this paper, we remedy this fact by presenting a thorough investigation of such models from three perspectives: Theory, Taxonomy, and Methods. First, we explore the theory behind the generalization of hybrid models from the Probably-Approximately-Correct (PAC) perspective. A consequence of our PAC guarantee is the existence of a sweet spot for the optimal transparency of the system. When such a sweet spot is attained, a hybrid model can potentially perform better than a standalone black box. Secondly, we provide a general taxonomy for the different ways of training hybrid models: the Post-Black-Box and Pre-Black-Box paradigms. These approaches differ in the order in which the interpretable and complex components are trained. We show where the state-of-the-art hybrid models Hybrid-Rule-Set and Companion-Rule-List fall in this taxonomy. Thirdly, we implement the two paradigms in a single method: HybridCORELS, which extends the CORELS algorithm to hybrid modeling. By leveraging CORELS, HybridCORELS provides a certificate of optimality of its interpretable component and precise control over transparency. We finally show empirically that HybridCORELS is competitive with existing hybrid models, and performs just as well as a standalone black box (or even better) while being partly transparent.

Exploiting Fairness to Enhance Sensitive Attributes Reconstruction

In recent years, a growing body of work has emerged on how to learn machine learning models under fairness constraints, often expressed with respect to some sensitive attributes. In this work, we consider the setting in which an adversary has black-box access to a target model and show that information about this model's fairness can be exploited by the adversary to enhance his reconstruction of the sensitive attributes of the training data. More precisely, we propose a generic reconstruction correction method, which takes as input an initial guess made by the adversary and corrects it to comply with some user-defined constraints (such as the fairness information) while minimizing the changes in the adversary's guess. The proposed method is agnostic to the type of target model, the fairness-aware learning method as well as the auxiliary knowledge of the adversary. To assess the applicability of our approach, we have conducted a thorough experimental evaluation on two state-of-the-art fair learning methods, using four different fairness metrics with a wide range of tolerances and with three datasets of diverse sizes and sensitive attributes. The experimental results demonstrate the effectiveness of the proposed approach to improve the reconstruction of the sensitive attributes of the training set.

Fooling SHAP with Stealthily Biased Sampling

SHAP explanations aim at identifying which features contribute the most to the difference in model prediction at a specific input versus a background distribution. Recent studies have shown that they can be manipulated by malicious adversaries to produce arbitrary desired explanations. However, existing attacks focus solely on altering the black-box model itself. In this paper, we propose a complementary family of attacks that leave the model intact and manipulate SHAP explanations using stealthily biased sampling of the data points used to approximate expectations w.r.t the background distribution. In the context of fairness audit, we show that our attack can reduce the importance of a sensitive feature when explaining the difference in outcomes between groups, while remaining undetected. These results highlight the manipulability of SHAP explanations and encourage auditors to treat post-hoc explanations with skepticism.

Characterizing the risk of fairwashing

Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanations' manipulation. However, to realize this, the post-hoc explanation model must produce different predictions than the original black-box on some inputs, leading to a decrease in the fidelity imposed by the difference in unfairness. In this paper, our main objective is to characterize the risk of fairwashing attacks, in particular by investigating the fidelity-unfairness trade-off. First, we demonstrate through an in-depth empirical study on black-box models trained on several real-world datasets and for several statistical notions of fairness that it is possible to build high-fidelity explanation models with low unfairness. For instance, we find that fairwashed explanation models can exhibit up to $99.20\%$ fidelity to the black-box models they explain while being $50\%$ less unfair. These results suggest that fidelity alone should not be used as a proxy for the quality of black-box explanations. Second, we show that fairwashed explanation models can generalize beyond the suing group (\emph{i.e.}, data points that are being explained), which will only worsen as more stable fairness methods get developed. Finally, we demonstrate that fairwashing attacks can transfer across black-box models, meaning that other black-box models can perform fairwashing without explicitly using their predictions.

Model extraction from counterfactual explanations

Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes. Among post-hoc explanation techniques, counterfactual explanations are becoming one of the most popular methods to achieve this objective. In particular, in addition to highlighting the most important features used by the black-box model, they provide users with actionable explanations in the form of data instances that would have received a different outcome. Nonetheless, by doing so, they also leak non-trivial information about the model itself, which raises privacy issues. In this work, we demonstrate how an adversary can leverage the information provided by counterfactual explanations to build high-fidelity and high-accuracy model extraction attacks. More precisely, our attack enables the adversary to build a faithful copy of a target model by accessing its counterfactual explanations. The empirical evaluation of the proposed attack on black-box models trained on real-world datasets demonstrates that they can achieve high-fidelity and high-accuracy extraction even under low query budgets.

GAMIN: An Adversarial Approach to Black-Box Model Inversion

Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been developed in the past in the black-box attack setting, in which the adversary does not have direct access to the structure of the model, few of these have been conducted so far against complex models such as deep neural networks. In this paper, we introduce GAMIN (for Generative Adversarial Model INversion), a new black-box model inversion attack framework achieving significant results even against deep models such as convolutional neural networks at a reasonable computing cost. GAMIN is based on the continuous training of a surrogate model for the target model under attack and a generator whose objective is to generate inputs resembling those used to train the target model. The attack was validated against various neural networks used as image classifiers. In particular, when attacking models trained on the MNIST dataset, GAMIN is able to extract recognizable digits for up to 60% of labels produced by the target. Attacks against skin classification models trained on the pilot parliament dataset also demonstrated the capacity to extract recognizable features from the targets.

Learning Fair Rule Lists

The widespread use of machine learning models, especially within the context of decision-making systems impacting individuals, raises many ethical issues with respect to fairness and interpretability of these models. While the research in these domains is booming, very few works have addressed these two issues simultaneously. To solve this shortcoming, we propose FairCORELS, a supervised learning algorithm whose objective is to learn at the same time fair and interpretable models. FairCORELS is a multi-objective variant of CORELS, a branch-and-bound algorithm, designed to compute accurate and interpretable rule lists. By jointly addressing fairness and interpretability, FairCORELS can achieve better fairness/accuracy tradeoffs compared to existing methods, as demonstrated by the empirical evaluation performed on real datasets. Our paper also contains additional contributions regarding the search strategies for optimizing the multi-objective function integrating both fairness, accuracy and interpretability.