6 papers · 1 filter
Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
Xingli Fang, Jung-Eun Kim
Prior approaches for membership privacy preservation usually update or retrain all weights in neural networks, which is costly and can lead to unnecessary utility loss or even more…
Decoupling Generalizability and Membership Privacy Risks in Neural Networks
Xingli Fang, Jung-Eun Kim
A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with u…
RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability
Vishwesh Sangarya, Jung-Eun Kim
As a strategy for sustainability of deep learning, reusing an existing model by retraining it rather than training a new model from scratch is critical. In this paper, we propose R…
Representation Magnitude has a Liability to Privacy Vulnerability
Xingli Fang, Jung-Eun Kim
The privacy-preserving approaches to machine learning (ML) models have made substantial progress in recent years. However, it is still opaque in which circumstances and conditions…
Center-Based Relaxed Learning Against Membership Inference Attacks
Xingli Fang, Jung-Eun Kim
Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, t…
Aggregate Representation Measure for Predictive Model Reusability
Vishwesh Sangarya, Richard Bradford, Jung-Eun Kim
In this paper, we propose a predictive quantifier to estimate the retraining cost of a trained model in distribution shifts. The proposed Aggregated Representation Measure (ARM) qu…