Meta-Learning with Evolutionary Strategy for Resilience Optimization of Image Recognition System
В’ячеслав Васильович Москаленко, Артем Геннадійович Коробов, Anton Kudravcev, М. В. Бойко · 2023
The problem of optimizing the resilience of image recognition systems to destructive disturbances has not yet been fully solved and is quite relevant for safety- critical applications. The task of optimizing the resilience of image recognition system to disturbing influences is a high- level task in relation to accuracy optimization, which determines the prospects of using the ideas and methods of meta-learning to solve it. Stated research goal is to develop an architectural add-ons and the meta-learning method for optimizing the resilience of an image recognition system to destructive disturbances. Meta-updating with evolutionary strategy is proposed for direct maximization of the expected value of resilience criterion. The experiments were conducted on a model with the ResNet-18 architecture, with an add-on in the form of convolutional adapters and meta- adapters for parallel correction of frozen pretrained modules. It has been experimentally confirmed that the proposed method provides a better resilience to random bit- flipinjection compared to training with fault injection by an average of 5.32%. Also, the proposed method provides a better resilience to adversarial evasion attacks compared to adversarial training by an average of 5.42%.