Differentially Private Instance Encoding against Privacy Attacks
TextHide was recently proposed to protect the training data via instance encoding in natural language domain. Due to the lack of theoretic privacy guarantee, such instance encoding scheme has been shown to be vulnerable against privacy attacks, e.g., reconstruction attack. To address such limitation, we revise the instance encoding scheme with differential privacy and thus provide a provable guarantee against privacy attacks. The experimental results also show that the proposed scheme can defend against privacy attacks while ensuring learning utility (as a trade-off).
Code (0)
등록된 구현이 없습니다.
Tasks
Reconstruction AttackSimilar Papers 제목 키워드 기반
Pan-Private Uniformity Testing
A centrally differentially private algorithm maps raw data to differentially private outputs. In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and…
Auditing Differentially Private Machine Learning: How Private is Private SGD?
We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realist…
Art AnalysisBIG-bench Machine LearningData PoisoningThe Influence of Dropout on Membership Inference in Differentially Private Models
Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers …
BIG-bench Machine LearningUncertainty QuantificationDifferentially Private Algorithms for Clustering with Stability Assumptions
We study the problem of differentially private clustering under input-stability assumptions. Despite the ever-growing volume of works on differential privacy in general and differentially private clustering in particular…
ClusteringNear-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment
In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback. For differentially private stochastic bandits, we propose both UCB and …
Thompson Sampling