公开(公告)号：US20210295210A1

公开(公告)日：2021-09-23

申请号：US16826478

申请日：2020-03-23

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Edward R. WETHERBEE ,  Kenneth P. BACLAWSKI ,  Guang C. WANG ,  Kenny C. GROSS ,  Anna CHYSTIAKOVA ,  Dieter GAWLICK ,  Zhen Hua LIU ,  Richard Paul SONDEREGGER

IPC: G06N20/00 ,  G06F17/16 ,  G06F17/18 ,  G06F30/27

Abstract: In one embodiment, a method for auditing the results of a machine learning model includes: retrieving a set of state estimates for original time series data values from a database under audit; reversing the state estimation computation for each of the state estimates to produce reconstituted time series data values for each of the state estimates; retrieving the original time series data values from the database under audit; comparing the original time series data values pairwise with the reconstituted time series data values to determine whether the original time series and reconstituted time series match; and generating a signal that the database under audit (i) has not been modified where the original time series and reconstituted time series match, and (ii) has been modified where the original time series and reconstituted time series do not match.

公开(公告)号：US20240265308A1

公开(公告)日：2024-08-08

申请号：US18615599

申请日：2024-03-25

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Edward R. WETHERBEE ,  Kenneth P. BACLAWSKI ,  Guang C. WANG ,  Kenny C. GROSS ,  Anna MORAV ,  Dieter GAWLICK ,  Zhen Hua LIU ,  Richard Paul SONDEREGGER

IPC: G06N20/00 ,  G05B23/02 ,  G06F17/16 ,  G06F17/18 ,  G06F30/27 ,  G06F111/10 ,  G06N3/08 ,  G06N20/10

CPC classification number: G06N20/00 ,  G05B23/024 ,  G06F17/16 ,  G06F17/18 ,  G06F30/27 ,  G06F2111/10 ,  G06N3/08 ,  G06N20/10

Abstract: Systems, methods, and other embodiments associated with auditing the results of a machine learning model are described. In one embodiment, a method accesses original time series data and machine learning estimates of the original time series data. The method generates reconstituted time series data from the machine learning estimates by reversing operations of a machine learning model trained for generating the machine learning estimates from the original time series data. The method detects tampering (or corruption) in the original time series data based on a difference between the original time series data and reconstituted time series data. And, the method generates an electronic verification report that indicates whether the tampering (or corruption) is detected in the original time series data.