# Improving Performance of Semi-Supervised Learning by Adversarial Attacks

Source: [Improving Performance of Semi-Supervised Learning by Adversarial Attacks](<https://www.sota2.com/research/paper/68fa70461e209131cea4a176>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:38:08.126Z

Authors: Dongyoon Yang, Kunwoong Kim, Yongdai Kim

Published: 2023-08-08T03:29:43.000Z

## Abstract

Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.04018>)

[PDF](<https://arxiv.org/pdf/2308.04018.pdf>)