Add to ORKGAlgorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods that offer minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse for linear and for differentiable classifiers. Finally, we show that regularizing the decision-making classifier to behave locally linearly and to rely more strongly on actionable features facilitates the existence of adve...
Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small...
Adversarial robustness has become a topic of growing interest in machine learning since it was obser...
Policy regularization methods such as maximum entropy regularization are widely used in reinforcemen...
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we inve...
Recent work has discussed the limitations of counterfactual explanations to recommend actions for al...
As machine learning models are increasingly being employed to make consequential decisions in real-w...
Different users of machine learning methods require different explanations, depending on their goals...
State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. ...
The recent years have been marked by extended research on adversarial attacks, especially on deep ne...
Recently it has been shown that many machine learning models are vulnerable to adversarial examples:...
Modern machine learning algorithms are able to reach an astonishingly high level of performance in ...
In this thesis we explore adversarial examples for simple model families and simple data distributio...
Algorithmic recourse recommendations inform stakeholders of how to act to revert unfavorable decisio...
International audienceDespite achieving impressive performance, state-of-the-art classifiers remain ...
Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computat...
Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small...
Adversarial robustness has become a topic of growing interest in machine learning since it was obser...
Policy regularization methods such as maximum entropy regularization are widely used in reinforcemen...
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we inve...
Recent work has discussed the limitations of counterfactual explanations to recommend actions for al...
As machine learning models are increasingly being employed to make consequential decisions in real-w...
Different users of machine learning methods require different explanations, depending on their goals...
State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. ...
The recent years have been marked by extended research on adversarial attacks, especially on deep ne...
Recently it has been shown that many machine learning models are vulnerable to adversarial examples:...
Modern machine learning algorithms are able to reach an astonishingly high level of performance in ...
In this thesis we explore adversarial examples for simple model families and simple data distributio...
Algorithmic recourse recommendations inform stakeholders of how to act to revert unfavorable decisio...
International audienceDespite achieving impressive performance, state-of-the-art classifiers remain ...
Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computat...
Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small...
Adversarial robustness has become a topic of growing interest in machine learning since it was obser...
Policy regularization methods such as maximum entropy regularization are widely used in reinforcemen...