2 papers
cs.CL2025
Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
Minyeong Choe, Haehyun Cho, Changho Seo +1
Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior wo…
cs.LG2025
SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
Minyeong Choe, Cheolhee Park, Changho Seo +1
Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attac…