Author

JaeYeon Park

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Feb 2026

Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

The Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy, is presented, establishing calibration integrity as a critical attack surface in federated learning.

Kichang Lee, Jaeho Jin, JaeYeon Park et al. · arXiv.org · 0 citations