Ricardo Mendes
4 papers · 2024–2025 · 3 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 · Bronze
Venues
Top co-authors
Research topics
Keywords
privacy leakage
(2)
model memorization
(2)
low-rank adaptation
(1)
sparse autoencoder
(1)
training data privacy
(1)
privacy protection
(1)
pre-trained language model
(1)
pii leakage
(1)
training data extraction
(1)
text anonymization
(1)
data extraction
(1)
personal identifiable information
(1)
private attribute
(1)
text utility
(1)
lora distillation
(1)
feature intervention
(1)
attribute leakage
(1)
prompt grounding
(1)
language model memorization
(1)
llm-based randomization
(1)
Papers
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
IJCNLP 2025
PII-Scope: A Comprehensive Study on Training Data Privacy Leakage in Pretrained LLMs
IJCNLP 2025
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
EMNLP 2025
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
ACL 2024