Non-vacuous generalization bounds for adversarial risk in stochastic neural networks

• Main Authors: WALEED, Mustafa, PHILIPP, Liznerski, LEDENT, Antoine, DENNIS, Wagner, PUYU, Wang, MARIUS, Kloft
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Bayesian; Generalisation; Generalization bound; Machine learning models; Neural-networks; Performance; Safety critical applications; Stochastic neural network; Test samples; Training data; Databases and Information Systems; Data Storage Systems
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/9306; https://ink.library.smu.edu.sg/context/sis_research/article/10306/viewcontent/mustafa24a.pdf

Adversarial examples are manipulated samples used to deceive machine learning models, posing a serious threat in safety-critical applications. Existing safety certificates for machine learning models are limited to individual input examples, failing to capture generalization to unseen data. To addre...