all AI news
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
April 11, 2024, 7:58 p.m. | Mike Young
DEV Community dev.to
Overview
- Proposed a method to significantly improve the trade-off between clean accuracy and adversarial robustness in neural classifiers
- Mixing output probabilities of a standard (high clean accuracy) and robust classifier, leveraging the robust classifier's confidence difference for correct and incorrect examples
- Theoretically certified the robustness of the mixed classifier under realistic assumptions
- Adapted an adversarial input detector to create a mixing network that adjusts the mixture adaptively, further reducing the accuracy penalty
- Empirically evaluated on CIFAR-100, achieving high clean accuracy …
accuracy adversarial classifier classifiers confidence difference examples improving mixed overview robust robustness standard trade trade-off via
More from dev.to / DEV Community
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Robotics Technician - 3rd Shift
@ GXO Logistics | Perris, CA, US, 92571