We initiate a formal study on the concept of learnable obfuscation and aim to answer the
following question: is there a type of data encoding that maintains the" learnability" of …

Privacy-preserving instance encoding aims to encode raw data into feature vectors without
revealing their privacy-sensitive information. When designed properly, these encodings can …

Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream
scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained over …

Diffusion models have a tendency to exactly replicate their training data, especially when
trained on small datasets. Most prior work has sought to mitigate this problem by imposing …

An ability to share data, even in aggregated form, is critical to advancing both conventional
and data science. However, insofar as such datasets are comprised of individuals, their …

Provable privacy typically requires involved analysis and is often associated with
unacceptable accuracy loss. While many empirical verification or approximation methods …

Federated Learning (FL) facilitates collaborative training of a global model whose
performance is boosted by private data owned by distributed clients, without compromising …

Linear regression is a fundamental tool for statistical analysis, which has motivated the
development of linear regression methods that satisfy provable privacy guarantees so that …

Data privacy protection is garnering increased attention among researchers. Diffusion
models (DMs), particularly with strict differential privacy, can potentially produce images with …

Machine learning models have recently enjoyed a significant increase in size and
popularity. However, this growth has created concerns about dataset privacy. To counteract …