# US 2021/0241119 A1 · Pre-trained model update device, pre-trained model update method, and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241119 A1 - Document ID: US20210241119A1 - Status: Published application - Kind: A1 - Application number: 17/050,583 - Filed: 2018-04-27 - Published: 2021-08-05 - Earliest claimed: 2018-04-27 - Assignees: NEC Corporation - Applicants: NEC Corporation - Inventors: Tsubasa TAKAHASHI; Kazuya KAKIZAKI - Web page: https://patentgrep.com/patent/US20210241119A1 ## CPC - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 3/045: Combinations of networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/047: Probabilistic or stochastic networks - G06N 3/0475: Generative networks - G06N 3/09: Supervised learning - G06N 3/094: Adversarial learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A pre-trained model update device includes: an alternative example generation unit configured to generate an alternative example and a correct answer label corresponding to the alternative example, based on a generative model representing training data used in generating a pre-trained model; an adversarial example generation unit configured to generate an adversarial example inducing the pre-trained model to misclassify and a correction label corresponding to the adversarial example, based on an attack model and based on the alternative example and the correct answer label generated by the alternative example generation unit; and a model update unit configured to perform additional learning based on a result of generation by the alternative example generation unit and a result of generation by the adversarial example generation unit, and generate an updated model. ## Claims ### Claim 1 A pre-trained model update device comprising: an alternative example generation unit configured to generate an alternative example and a correct answer label corresponding to the alternative example, based on a generative model representing training data used in generating a pre-trained model; an adversarial example generation unit configured to generate an adversarial example inducing the pre-trained model to misclassify and a correction label corresponding to the adversarial example, based on an attack model and based on the alternative example and the correct answer label generated by the alternative example generation unit; and a model update unit configured to perform additional learning based on a result of generation by the alternative example generation unit and a result of generation by the adversarial example generation unit, and generate an updated model. ### Claim 2 (depends on 1) The pre-trained model update device according to claim 1, further comprising: a generative model building unit configured to generate the generative model based on the training data used in generating the pre-trained model; and a storage unit configured to have the generative model built by the generative model building unit stored therein, wherein the alternative example generation unit is configured to generate the alternative example and the correct answer label corresponding to the alternative example, based on the generative model stored in the storage unit. ### Claim 3 (depends on 2) The pre-trained model update device according to claim 2, wherein the generative model building unit is configured to use Conditional Generative Adversarial Networks when generating the generative model corresponding to the training data. ### Claim 4 (depends on 2) The pre-trained model update device according to claim 2, wherein the generative model building unit is configured to use Conditional Variational Auto Encoder when generating the generative model corresponding to the training data. ### Claim 5 (depends on 1) The pre-trained model update device according to claim 1, wherein the model update unit is configured to repeatedly update the updated model generated by the model update unit until a given condition is satisfied. ### Claim 6 (depends on 5) The pre-trained model update device according to claim 5, wherein the model update unit is configured to update the updated model by using the adversarial example and the correction label that are newly generated by the adversarial example generation unit every time updating the updated model. ### Claim 7 (depends on 5) The pre-trained model update device according to claim 5, wherein the model update unit is configured to repeatedly update the updated model until a given condition is satisfied by using the same adversarial example and the same correction label. ### Claim 8 (depends on 5) The pre-trained model update device according to claim 5, wherein the model update unit is configured to repeatedly update the updated model generated by the model update unit a previously determined given number of times. ### Claim 9 (depends on 5) The pre-trained model update device according to claim 5, wherein the model update unit is configured to repeatedly update the updated model until accuracy of classification in which the correction label is a classification result for the adversarial example exceeds a given threshold value. ### Claim 10 (depends on 1) The pre-trained model update device according to claim 1, wherein the adversarial example generation unit is configured to generate the adversarial example and the correction label that correspond to each of a plurality of attack models. ### Claim 11 (depends on 9) The pre-trained model update device according to claim 9, wherein the model update unit is configured to, after performing additional learning based on the adversarial example and the correction label that correspond to a first attack model and generating the updated model, perform additional learning based on the adversarial example and the correction label that correspond to a second attack model and update the generated updated model. ### Claim 12 A pre-trained model update method executed by a pre-trained model update device, the pre-trained model update method comprising: generating an alternative example and a correct answer label corresponding to the alternative example, based on a generative model representing training data used in generating a pre-trained model; generating an adversarial example inducing the pre-trained model to misclassify and a correction label corresponding to the adversarial example, based on an attack model and based on the alternative example and the correct answer label generated by the alternative example generation unit; and performing additional learning based on the alternative example and the correct answer label and based on the adversarial example and the correction label, and generating an updated model. ### Claim 13 A non-transitory computer-readable recording medium having a computer program recorded thereon, the computer program comprising instructions for causing a pre-trained model update device to realize: an alternative example generation unit configured to generate an alternative example and a correct answer label corresponding to the alternative example, based on a generative model representing training data used in generating a pre-trained model; an adversarial example generation unit configured to generate an adversarial example inducing the pre-trained model to misclassify and a correction label corresponding to the adversarial example, based on an attack model and based on the alternative example and the correct answer label generated by the alternative example generation unit; and a model update unit configured to perform additional learning based on a result of generation by the alternative example generation unit and a result of generation by the adversarial example generation unit, and generate an updated model.