Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.
Mask- based membership inference attacks for retrieval- augmented generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Privacy of LLMs: An Ablation Study
Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.