2 papers
cs.CR2026
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree +2
Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets. Ensuring th…
cs.LG2026
Batch Normalization Amplifies Memorization and Privacy Risks
Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani
Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remain…