1 citations · 1 across the 10 of their papers we have counts for
6 papers · 1 filter
CALLIOPE: Private Insights into AI Use, Without Embeddings
Edith Cohen, Vadym Doroshenko, Badih Ghazi +11
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy…
Extractable Memorization From First Principles
A. Feder Cooper, Marika Swanberg, Jamie Hayes +6
Recent work on extractable memorization in language models suffers from two contrasting validity problems. Some studies overstate extraction, for example, by using sequences too sh…
Privacy in Metalearning and Multitask Learning: Modeling and Separations
Maryam Aliakbarpour, Konstantina Bairaktari, Adam Smith +2
Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop indiv…
Measuring memorization in language models via probabilistic extraction
Jamie Hayes, Marika Swanberg, Harsh Chaudhari +6
Large language models (LLMs) are susceptible to memorizing training data, raising concerns about the potential extraction of sensitive information at generation time. Discoverable…
Auditing Privacy Mechanisms via Label Inference Attacks
Róbert István Busa-Fekete, Travis Dick, Claudio Gentile +3
We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer t…
Differentially Private Sampling from Distributions
Sofya Raskhodnikova, Satchit Sivakumar, Adam Smith +1
We initiate an investigation of private sampling from distributions. Given a dataset with independent observations from an unknown distribution , a sampling algorithm must o…