Auditing classifier models with adversarially robust xai committees
AssigneeDell Products L.P.
InventorsIam Palatnik de Sousa, Adriana Bechara Prado
Life of this patent
Estimating the term…
Abstract
A method includes assembling an explainable artificial intelligence committee comprising two or more explainable artificial intelligence techniques, performing the explainable artificial intelligence techniques on results generated by a machine learning model, as a result of the performing, obtaining respective explanations, generated by each of the explainable artificial intelligence techniques, for the results generated by the machine learning model, and determining that one of the explanations was compromised by an attacker.
Claims20
A method, comprising:
- assembling an explainable artificial intelligence committee comprising two or more explainable artificial intelligence techniques;
- performing the explainable artificial intelligence techniques on results generated by a machine learning model;
- as a result of the performing, obtaining respective explanations, generated by each of the explainable artificial intelligence techniques, for the results generated by the machine learning model;
- and
- determining that one of the explanations was compromised by an attacker.
A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
- assembling an explainable artificial intelligence committee comprising two or more explainable artificial intelligence techniques;
- performing the explainable artificial intelligence techniques on results generated by a machine learning model;
- as a result of the performing, obtaining respective explanations, generated by each of the explainable artificial intelligence techniques, for the results generated by the machine learning model;
- and
- determining that one of the explanations was compromised by an attacker.
Dependencies are inferred from the claim text.