Membership Encoding for Deep Learning
Explore this paper's citation graph
Summary
This paper presents membership encoding for training deep neural networks and encoding the membership information, i.e. whether a data point is used for training, for a subset of training data, and the encoding algorithm can determine the membership of significantly redacted data points.
- Type
- preprint
- Published
- 2019-09-27
- Cited by
- 6
- References
- 45
- Access
- Open access
- OpenAlex
- https://openalex.org/W2976230761
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:203593891
Keywords
Encoding (memory), Computer science, Embedding, Digital watermarking, Deep learning
References
- Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Resolving Individuals Contributing Trace Amounts of DNA to Highly Complex Mixtures Using High-Density SNP Genotyping Microarrays
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
- Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers
- Gradient-based learning applied to document recognition
- Compressing Neural Networks with the Hashing Trick
- Deep Residual Learning for Image Recognition
- Robust Traceability from Trace Amounts
- Model compression
- Membership Privacy in MicroRNA-based Studies
- Membership Inference Attacks Against Machine Learning Models
- Understanding deep learning requires rethinking generalization
- Embedding Watermarks into Deep Neural Networks
- Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Knock Knock, Who's There? Membership Inference on Aggregate Location Data
- Machine Learning Models that Remember Too Much
- Understanding Membership Inferences on Well-Generalized Learning Models
- Stealing Hyperparameters in Machine Learning
Cited by
- You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks
- Membership Encoding for Black-Box Neural Network Watermarking
- Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
- Node-Level Membership Inference Attacks Against Graph Neural Networks
- UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run
- ODE -L EVEL M EMBERSHIP I NFERENCE A TTACKS
Related papers
- Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning
- Reconciling Utility and Membership Privacy via Knowledge Distillation
- Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
- Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary
- Sharing Models or Coresets: A Study based on Membership Inference Attack
- A Framework to Preserve User Privacy for Machine Learning as a Service
- NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
- Defending CNN against privacy leakage in edge computing via binary neural networks