REVIEW 2 cited by
Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The adoption of artificial intelligence (AI) across industries has led to the widespread use of complex black-box models and interpretation tools for decision making. This paper proposes an adversarial framework to uncover the vulnerability of permutation-based interpretation methods for machine learning tasks, with a particular focus on partial dependence (PD) plots. This adversarial framework modifies the original black box model to manipulate its predictions for instances in the extrapolation domain. As a result, it produces deceptive PD plots that can conceal discriminatory behaviors while preserving most of the original model's predictions. This framework can produce multiple fooled PD plots via a single model. By using real-world datasets including an auto insurance claims dataset and COMPAS (Correctional Offender Management Profiling for Alternative Sanctions) dataset, our results show that it is possible to intentionally hide the discriminatory behavior of a predictor and make the black-box model appear neutral through interpretation tools like PD plots while retaining almost all the predictions of the original black-box model. Managerial insights for regulators and practitioners are provided based on the findings.
Forward citations
Cited by 2 Pith papers
-
From Point to probabilistic gradient boosting for claim frequency and severity prediction
A benchmark of ten gradient boosting algorithms on five insurance datasets shows probabilistic versions can improve fit without losing predictive accuracy, with LightGBM and XGBoostLSS fastest.
-
Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
A review-style position paper that separates the choice of value function from the choice of an efficient allocation, presenting Weber and Harsanyi sets as generalizations of Shapley values.
Discussion (0). Continue with ORCID to comment.