5 papers
FedSGT: Exact Federated Unlearning via Sequential Group-based Training
Bokang Zhang, Hong Guan, Hong kyu Lee +3
Federated Learning (FL) enables collaborative, privacy-preserving model training, but supporting the "Right to be Forgotten" is especially challenging because data influences the m…
CACTUSDB: Unlock Co-Optimization Opportunities for SQL and AI/ML Inferences
Lixi Zhou, Kanchan Chowdhury, Lulu Xie +5
There is a growing demand for supporting inference queries that combine Structured Query Language (SQL) and Artificial Intelligence / Machine Learning (AI/ML) model inferences in d…
InferF: Declarative Factorization of AI/ML Inferences over Joins
Kanchan Chowdhury, Lixi Zhou, Lulu Xie +2
Real-world AI/ML workflows often apply inference computations to feature vectors joined from multiple datasets. To avoid the redundant AI/ML computations caused by repeated data re…
Privacy and Accuracy-Aware AI/ML Model Deduplication
Hong Guan, Lei Yu, Lixi Zhou +5
With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on…
Declarative Privacy-Preserving Inference Queries
Hong Guan, Ansh Tiwari, Summer Gautier +8
Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackl…