Variational Encoder-based Reliable Classification

Authors: Chitresh Bhushan, Zhaoyuan Yang, Nurali Virani, Naresh Iyer
Published: 2020-02-19 | Updated: 2020-10-17

Source: https://arxiv.org/abs/2002.08289

PDF: https://arxiv.org/pdf/2002.08289

AIにより推定されたラベル

敵対的攻撃検出 トレーニング手法 ロバスト性評価

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Machine learning models provide statistically impressive results which might be individually unreliable. To provide reliability, we propose an Epistemic Classifier (EC) that can provide justification of its belief using support from the training dataset as well as quality of reconstruction. Our approach is based on modified variational auto-encoders that can identify a semantically meaningful low-dimensional space where perceptually similar instances are close in ℓ₂-distance too. Our results demonstrate improved reliability of predictions and robust identification of samples with adversarial attacks as compared to baseline of softmax-based thresholding.