From 99d798a9f6a10e57d70468a2b9f876091c769e91 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Wed, 30 Dec 2020 06:07:26 -0500 Subject: [PATCH 1/2] Add more papers --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 4526a4f..c52fe80 100644 --- a/README.md +++ b/README.md @@ -68,6 +68,7 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Bootstrap Aggregation for Point-based Generalized Membership Inference Attacks**](https://arxiv.org/abs/2011.08738) (Felps et al., 2020) - [**Differentially Private Learning Does Not Bound Membership Inference**](https://arxiv.org/abs/2010.12112) (Humphries et al., 2020) - [**Quantifying Membership Privacy via Information Leakage**](https://arxiv.org/abs/2010.05965) (Saeidian et al., 2020) +- [**Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning**](https://arxiv.org/abs/1906.00389) (Yaghini et al., 2020) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. @@ -145,6 +146,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles**](https://arxiv.org/abs/2009.09560) (Yuan et al., 2020) - [**Black-Box Ripper: Copying black-box models using generative evolutionary algorithms**](https://arxiv.org/abs/2010.11158) (Barbalau et al., 2020) ([code](https://github.com/antoniobarbalau/black-box-ripper)) - [**Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization**](https://arxiv.org/abs/2010.12751) (Wu et al., 2020) +- [**Extracting Training Data from Large Language Models**](https://arxiv.org/abs/2012.07805) (Carlini et al., 2020) # Other - [**Toward Robustness and Privacy in Federated Learning: Experimenting with Local and Central Differential Privacy**](https://arxiv.org/abs/2009.03561) (Naseri et al., 2020) @@ -153,3 +155,5 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Information Leakage in Embedding Models**](https://arxiv.org/abs/2004.00053) (Song and Raghunathan, 2020) - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) - [**Synthetic Data -- A Privacy Mirage**](https://arxiv.org/abs/2011.07018) (Stadler et al., 2020) +- [**Robust Membership Encoding: Inference Attacks and CopyrightProtection for Deep Learning**](https://arxiv.org/pdf/1909.12982.pdf) (Song and Shokri, 2020) +- [**Quantifying Privacy Leakage in Graph Embedding**](https://arxiv.org/abs/2010.00906) (Duddu et al., 2020) From dfede8d43dce64c2f097280caa15d097275cc937 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Fri, 1 Jan 2021 01:05:33 -0500 Subject: [PATCH 2/2] Add property inference paper --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c52fe80..b056ff3 100644 --- a/README.md +++ b/README.md @@ -113,6 +113,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Property inference attacks on fully connected neural networks using permutation invariant representations**](https://dl.acm.org/doi/pdf/10.1145/3243734.3243834) (Ganju et al., 2018) - [**Exploiting unintended feature leakage in collaborative learning**](https://ieeexplore.ieee.org/iel7/8826229/8835208/08835269.pdf) (Melis et al., 2019) ([code](https://github.com/csong27/property-inference-collaborative-ml)) - [**Overlearning Reveals Sensitive Attributes**](https://openreview.net/pdf?id=SJeNz04tDS) (Song C. et al., 2020) ([code](https://drive.google.com/file/d/1hu0PhN3pWXe6LobxiPFeYBm8L-vQX2zJ/view?usp=sharing)) +- [**Subject Property Inference Attack in Collaborative Learning**](https://ieeexplore.ieee.org/document/9204357) (Xu and Li, 2020) ## Model extraction - [**Stealing machine learning models via prediction apis**](https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf) (Tramèr et al., 2016) ([code](https://github.com/ftramer/Steal-ML))