Santiago Zanella-Beguelin
4 papers · 2021–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Keywords
membership inference attack
(2)
large language model
(2)
adversarial attack
(2)
posterior estimation
(1)
autoregressive model
(1)
synthetic data
(1)
confidence interval
(1)
privacy budget
(1)
fine-tuning attack
(1)
privacy risk
(1)
security evaluation
(1)
membership inference
(1)
prompt injection
(1)
model extraction
(1)
defense mechanism
(1)
security vulnerability
(1)
natural language model
(1)
grey-box setting
(1)
algebraic attack
(1)
embedding extraction
(1)