From 85705e312b49fa26cabd7ed344fa89757fc8f427 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Tue, 15 Sep 2020 15:23:01 -0400 Subject: [PATCH 1/4] Add more papers --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 40ea973..4615f57 100644 --- a/README.md +++ b/README.md @@ -56,6 +56,8 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries**](https://arxiv.org/abs/2009.00395) (Rahimian et al., 2020) - [**Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation**](https://arxiv.org/abs/1912.09685) (He et al., 2019) - [**Differential Privacy Defenses and Sampling Attacks for Membership Inference**](https://priml-workshop.github.io/priml2019/papers/PriML2019_paper_47.pdf) (Rahimian et al., 2019) +- [**privGAN: Protecting GANs from membership inference attacks at low cost**](https://arxiv.org/abs/2001.00071) (Mukherjee et al., 2020) +- [**Sharing Models or Coresets: A Study based on Membership Inference Attack**](https://arxiv.org/abs/2007.02977) (Lu et al., 2020) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. @@ -90,6 +92,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Reducing Risk of Model Inversion Using Privacy-Guided Training**](https://arxiv.org/abs/2006.15877) (Goldsteen et al., 2020) - [**Robust Transparency Against Model Inversion Attacks**](https://ieeexplore.ieee.org/abstract/document/9178452) (Alufaisan et al., 2020) - [**Does AI Remember? Neural Networks and the Right to be Forgotten**](https://uwspace.uwaterloo.ca/handle/10012/15754) (Graves et al., 2020) +- [**Improving Robustness to Model Inversion Attacks via Mutual Information Regularization**](https://arxiv.org/abs/2009.05241) (Wang et al., 2020) ## Property inference - [**Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers**](https://dl.acm.org/doi/10.1504/IJSN.2015.071829) (Ateniese et al., 2015) @@ -125,6 +128,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Model extraction from counterfactual explanations**](https://arxiv.org/abs/2009.01884) (Aïvodji et al., 2020) - [**MetaSimulator: Simulating Unknown Target Models for Query-Efficient Black-box Attacks**](https://arxiv.org/abs/2009.00960) (Chen and Yong, 2020) - [**Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks**](https://arxiv.org/abs/1906.10908) (Orekondy et al., 2019) +- [**IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis**](https://arxiv.org/abs/2006.10720) (Hajipour et al., 2020) # Other - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) From 8d64c8d5722167d34008a5006487916e29026329 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Tue, 15 Sep 2020 15:33:32 -0400 Subject: [PATCH 2/4] Add more papers --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 4615f57..9fe12b9 100644 --- a/README.md +++ b/README.md @@ -58,6 +58,9 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Differential Privacy Defenses and Sampling Attacks for Membership Inference**](https://priml-workshop.github.io/priml2019/papers/PriML2019_paper_47.pdf) (Rahimian et al., 2019) - [**privGAN: Protecting GANs from membership inference attacks at low cost**](https://arxiv.org/abs/2001.00071) (Mukherjee et al., 2020) - [**Sharing Models or Coresets: A Study based on Membership Inference Attack**](https://arxiv.org/abs/2007.02977) (Lu et al., 2020) +- [**Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning**](https://arxiv.org/abs/2009.04872) (Zou et al., 2020) +- [**Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics**](https://arxiv.org/abs/2009.05669) (Bentley et al., 2020) +- [**MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models**](https://arxiv.org/abs/2009.05683) (Liu et al., 2020) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. @@ -93,6 +96,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Robust Transparency Against Model Inversion Attacks**](https://ieeexplore.ieee.org/abstract/document/9178452) (Alufaisan et al., 2020) - [**Does AI Remember? Neural Networks and the Right to be Forgotten**](https://uwspace.uwaterloo.ca/handle/10012/15754) (Graves et al., 2020) - [**Improving Robustness to Model Inversion Attacks via Mutual Information Regularization**](https://arxiv.org/abs/2009.05241) (Wang et al., 2020) +- [**SAPAG: A Self-Adaptive Privacy Attack From Gradients**](https://arxiv.org/abs/2009.06228) (Wang et al., 2020) ## Property inference - [**Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers**](https://dl.acm.org/doi/10.1504/IJSN.2015.071829) (Ateniese et al., 2015) From a472f3105503216f18195df661a967de518ca099 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Sun, 20 Sep 2020 21:43:05 -0400 Subject: [PATCH 3/4] Add new paper; concerns about classification --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 9fe12b9..3d70491 100644 --- a/README.md +++ b/README.md @@ -135,4 +135,5 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis**](https://arxiv.org/abs/2006.10720) (Hajipour 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) - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) From 92d3b70bff0f8c27a18dcb28b6aed78468bb8042 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Mon, 28 Sep 2020 17:23:31 -0400 Subject: [PATCH 4/4] Update README.md --- README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/README.md b/README.md index 3d70491..595b301 100644 --- a/README.md +++ b/README.md @@ -61,6 +61,8 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning**](https://arxiv.org/abs/2009.04872) (Zou et al., 2020) - [**Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics**](https://arxiv.org/abs/2009.05669) (Bentley et al., 2020) - [**MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models**](https://arxiv.org/abs/2009.05683) (Liu et al., 2020) +- [**On Primes, Log-Loss Scores and (No) Privacy**](https://arxiv.org/abs/2009.08559) (Aggarwal et al., 2020) +- [**MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks**](https://arxiv.org/abs/2008.13578) (Wang et al., 2020) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. @@ -133,7 +135,11 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**MetaSimulator: Simulating Unknown Target Models for Query-Efficient Black-box Attacks**](https://arxiv.org/abs/2009.00960) (Chen and Yong, 2020) - [**Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks**](https://arxiv.org/abs/1906.10908) (Orekondy et al., 2019) - [**IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis**](https://arxiv.org/abs/2006.10720) (Hajipour et al., 2020) +- [**ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles**](https://arxiv.org/abs/2009.09560) (Yuan 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) +- [**Analyzing Information Leakage of Updates to Natural Language Models**](https://arxiv.org/abs/1912.07942) (Brockschmidt et al., 2020) +- [**Estimating g-Leakage via Machine Learning**](https://arxiv.org/abs/2005.04399) (Romanelli et al., 2020) +- [**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)