Invention Grant
- Patent Title: Protecting cognitive systems from gradient based attacks through the use of deceiving gradients
-
Application No.: US15800697Application Date: 2017-11-01
-
Publication No.: US10657259B2Publication Date: 2020-05-19
- Inventor: Taesung Lee , Ian M. Molloy , Farhan Tejani
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent Stephen J. Walder, Jr.; Jeffrey S. LaBaw
- Main IPC: G06F21/56
- IPC: G06F21/56 ; G06F21/57 ; G06N3/02

Abstract:
Mechanisms are provided for providing a hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to introduce noise in internal feature representations of the hardened neural network. The noise introduced in the internal feature representations diverts gradient computations associated with a loss surface of the hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to implement a merge layer of nodes that combine outputs of adversarially trained output nodes of the hardened neural network with output nodes of the hardened neural network trained based on the introduced noise. The mechanisms process, by the hardened neural network, input data to generate classification labels for the input data and thereby generate augmented input data which is output to a computing system for processing to perform a computing operation.
Public/Granted literature
- US20190130110A1 Protecting Cognitive Systems from Gradient Based Attacks through the Use of Deceiving Gradients Public/Granted day:2019-05-02
Information query