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
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US