Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
An Investigation of Memorization Risk in Healthcare Foundation Models
Sana Tonekaboni, Lena Stempfle, Adibvafa Fallahpour +2
Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient informat…
cs.LG2025
When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
Yuxin Xiao, Sana Tonekaboni, Walter Gerych +2
Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments th…