Method, system and processor for enhancing robustness of source-code classification model

A system for enhancing robustness of a source-code classification model, based on invariant features, wherein the system comprises a processor and a storage medium, wherein the processor is configured to execute a computer program stored in the storage medium in the form of a computer program to be executed by the processor, wherein the computer program comprises:

• a training set-expanding module, for combining to combine non-robustness features to generate a plurality of different style templates, converting codes in an input code training set into new codes of different styles based on the plurality of different style templates, using a code conversion program, so as to obtain a converted-code training set composed of the new codes, merging the input code training set and the converted-code training set into an expanded training set, and converting code texts in the expanded training set into code images;
• and
• a model-training module, for converting to convert the code images into vectors required by model training through data pre-processing, randomly picking samples of an identical class from the expanded training set, pairing the samples into matched sample pairs, and inputting the matched sample pairs into a feature extractor, iteratively updating the feature extractor to extract invariant features and the matched sample pairs by means of contrastive learning and extracting target characteristics, and training the extracted invariant features in a classifier, so as to produce a source-code classification model with enhanced robustness,
• wherein the step of iteratively updating the feature extractor and the matched sample pairs by the means of contrastive learning and extracting the target characteristics comprises:
• dividing the source-code classification model into two parts, namely the feature extractor and the classifier, inputting the randomly picked pairs of the samples of the identical class matched sample pairs into the feature extractor, figuring out differences among the samples using a contrastive loss function, iteratively updating the feature extractor and the matched sample pairs, replacing the randomly picked sample samples paired into the matched sample pairs with new sample pairs, and performing training the feature extractor iteratively until training of the feature extractor reaches convergence, wherein the loss function is a cross-entropy loss function and the target characteristics are invariant high-robustness features.