ECINN: Efficient Counterfactuals from Invertible Neural Networks
Frederik Hvilshøj,
Alexandros Iosifidis,
Ira Assent
Abstract:Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We propose a method, ECINN, that utilizes the generative capacities of invertible neural networks for image classification to generate counterfactual examples efficiently. In contrast to competing methods that sometimes need a thousand evaluations or more of the classifier, ECINN has a closed-form expression and generates a counterfactual… Show more
“…For counterfactual observation generation, numerous methods have been proposed [176], [177], [178]. While these generally need to query an underlying model multiple times, efficient methods utilizing invertible neural networks have also been proposed [179]. A related problem concerns the quantitative evaluation of counterfactual examples; see the work by Hvilshøj et al [180] for an in-depth discussion.…”
Section: Interpretable and Fair Machine Learningmentioning
Money laundering is a profound global problem. Nonetheless, there is little scientific literature on statistical and machine learning methods for anti-money laundering. In this paper, we focus on anti-money laundering in banks and provide an introduction and review of the literature. We propose a unifying terminology with two central elements: (i) client risk profiling and (ii) suspicious behavior flagging. We find that client risk profiling is characterized by diagnostics, i.e., efforts to find and explain risk factors. On the other hand, suspicious behavior flagging is characterized by non-disclosed features and hand-crafted risk indices. Finally, we discuss directions for future research. One major challenge is the need for more public data sets. This may potentially be addressed by synthetic data generation. Other possible research directions include semi-supervised and deep learning, interpretability, and fairness of the results.INDEX TERMS Anti-money laundering, know-your-client, machine learning, literature review.
“…For counterfactual observation generation, numerous methods have been proposed [176], [177], [178]. While these generally need to query an underlying model multiple times, efficient methods utilizing invertible neural networks have also been proposed [179]. A related problem concerns the quantitative evaluation of counterfactual examples; see the work by Hvilshøj et al [180] for an in-depth discussion.…”
Section: Interpretable and Fair Machine Learningmentioning
Money laundering is a profound global problem. Nonetheless, there is little scientific literature on statistical and machine learning methods for anti-money laundering. In this paper, we focus on anti-money laundering in banks and provide an introduction and review of the literature. We propose a unifying terminology with two central elements: (i) client risk profiling and (ii) suspicious behavior flagging. We find that client risk profiling is characterized by diagnostics, i.e., efforts to find and explain risk factors. On the other hand, suspicious behavior flagging is characterized by non-disclosed features and hand-crafted risk indices. Finally, we discuss directions for future research. One major challenge is the need for more public data sets. This may potentially be addressed by synthetic data generation. Other possible research directions include semi-supervised and deep learning, interpretability, and fairness of the results.INDEX TERMS Anti-money laundering, know-your-client, machine learning, literature review.
“…Interactive explainability. It could be fruitful to base explainable verification methods on counterfactual explanation techniques for AI [67]. Counterfactuals provide an understanding into AI models by identifying similar inputs with changes in decisive properties that lead to a different model outcome than the one under study.…”
In 2020, the EU launched its sustainable and smart mobility strategy, outlining how it plans to have a 90% reduction in transport emission by 2050. Central to achieving this goal will be the improvement of rail technology, with many new data-driven visionary systems being proposed. AI will be the enabling technology for many of those systems. However, safety and security guarantees will be key for wide-spread acceptance and uptake by Industry and Society. Therefore, suitable verification and validation techniques are needed. In this article, we argue how formal methods research can contribute to the development of modern Railway systems -which may or may not make use of AI techniques -and present several research problems and techniques worth to be further considered.
“…For counterfactual observation generation, numerous methods have been proposed [1,19,38]. While these generally need to query an underlying model multiple times, efficient methods utilizing invertible neural networks have also been proposed [52]. A related problem concerns the quantitative evaluation of counterfactual examples; see the work by Hvilshøj et al [53] for an in-depth discussion.…”
Section: Interpretable and Fair Machine Learningmentioning
Money laundering is a profound, global problem. Nonetheless, there is little statistical and machine learning research on the topic. In this paper, we focus on anti-money laundering in banks. To help organize existing research in the field, we propose a unifying terminology and provide a review of the literature. This is structured around two central tasks: (i) client risk profiling and (ii) suspicious behavior flagging. We find that client risk profiling is characterized by diagnostics, i.e., efforts to find and explain risk factors. Suspicious behavior flagging, on the other hand, is characterized by non-disclosed features and hand-crafted risk indices. Finally, we discuss directions for future research. One major challenge is the lack of public data sets. This may, potentially, be addressed by synthetic data generation. Other possible research directions include semi-supervised and deep learning, interpretability and fairness of the results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.