US 11,916,931 B2
Methods for protecting pattern classification node from malicious requests and related networks and nodes
Konstantinos Vandikas, Solna (SE); Leonid Mokrushin, Uppsala (SE); Maxim Teslenko, Sollentuna (SE); Daniel Lindström, Luleå (SE); and Marin Orlic, Bromma (SE)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Appl. No. 17/606,111
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Apr. 24, 2019, PCT No. PCT/EP2019/060529
§ 371(c)(1), (2) Date Oct. 25, 2021,
PCT Pub. No. WO2020/216442, PCT Pub. Date Oct. 29, 2020.
Prior Publication US 2022/0311784 A1, Sep. 29, 2022
Int. Cl. H04L 9/40 (2022.01); G06N 3/04 (2023.01)
CPC H04L 63/1416 (2013.01) [G06N 3/04 (2013.01); H04L 63/1425 (2013.01); H04L 63/1491 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by a protection node for protecting a pattern classification node from malicious requests, the method comprising:
receiving, from a user node a request containing an original pattern to be classified by a machine learning algorithm performed by the pattern classification node;
adding noise to the original pattern to generate a noisy pattern;
obtaining a first classification of the noisy pattern based on processing of the noisy pattern by a first clone of the machine learning algorithm performed by the protection node;
obtaining a second classification of the original pattern based on forwarding the request for processing of the original pattern by the machine learning algorithm performed by the pattern classification node;
comparing the first and second classifications to determine whether the first and second classifications satisfy a defined similarity rule; and
using the comparison to manage the request from the user node.