3 papers
cs.LG2026
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fall…
cs.LG2025
Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gra…
cs.CR2025
Verifiable Dropout: Turning Randomness into a Verifiable Claim
Kichang Lee, Sungmin Lee, Jaeho Jin +1
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address t…