From 6d4a44edeb0f6be6cb367a2b5ac9e516f24f9f92 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Mon, 7 Sep 2020 17:12:28 -0400 Subject: [PATCH 1/6] Add more papers --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 92b8dde..fcd3f85 100644 --- a/README.md +++ b/README.md @@ -83,6 +83,8 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Illuminating the Dark or how to recover what should not be seen in FE-based classifiers**](https://eprint.iacr.org/2018/1001) (Carpov et al., 2020) - [**Evaluation Indicator for Model Inversion Attack**](https://drive.google.com/file/d/1rl77BGtGHzZ8obWUEOoqunXCjgvpzE8d/view) (Tanaka et al., 2020) - [**Understanding Unintended Memorization in Federated Learning**](https://arxiv.org/abs/2006.07490) (Thakkar et al., 2020) +- [**An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack**](https://ieeexplore.ieee.org/document/8822435) (Park et al., 2019) +- [**Reducing Risk of Model Inversion Using Privacy-Guided Training**](https://arxiv.org/abs/2006.15877) (Goldsteen 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 d21f27aec0f29b625e993436537501cac50913b9 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Mon, 7 Sep 2020 17:26:22 -0400 Subject: [PATCH 2/6] Add more papers --- README.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index fcd3f85..e8b5648 100644 --- a/README.md +++ b/README.md @@ -52,7 +52,7 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Label-Only Membership Inference Attacks**](https://arxiv.org/abs/2007.14321) (Choquette Choo et al., 2020) - [**Label-Leaks: Membership Inference Attack with Label**](https://arxiv.org/abs/2007.15528) (Li and Zhang, 2020) - [**Alleviating Privacy Attacks via Causal Learning**](https://arxiv.org/abs/1909.12732) (Tople et al., 2020) - +- [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. @@ -85,6 +85,8 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Understanding Unintended Memorization in Federated Learning**](https://arxiv.org/abs/2006.07490) (Thakkar et al., 2020) - [**An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack**](https://ieeexplore.ieee.org/document/8822435) (Park et al., 2019) - [**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) ## 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) @@ -115,4 +117,5 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**How to 0wn NAS in Your Spare Time**](https://arxiv.org/abs/2002.06776) (Hong et al., 2020) - [**Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks**](https://arxiv.org/abs/1810.03487) (Hong et al., 2020) - [**Reverse-Engineering Deep ReLU Networks**](https://proceedings.icml.cc/static/paper_files/icml/2020/1-Paper.pdf) (Rolnick and Kording, 2020) - +- [**Model Extraction Oriented Data Publishing with k-anonymity**](https://link.springer.com/chapter/10.1007/978-3-030-58208-1_13) (Fukuoka et al., 2020) +- [**Hermes Attack: Steal DNN Models with Lossless Inference Accuracy**](https://arxiv.org/abs/2006.12784) (Zhu et al., 2020) From f3c77a000d03cca1b0e84b98f2b2fdc42c5900c3 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Mon, 7 Sep 2020 17:32:19 -0400 Subject: [PATCH 3/6] Add more papers --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index e8b5648..1b2f37d 100644 --- a/README.md +++ b/README.md @@ -52,6 +52,7 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Label-Only Membership Inference Attacks**](https://arxiv.org/abs/2007.14321) (Choquette Choo et al., 2020) - [**Label-Leaks: Membership Inference Attack with Label**](https://arxiv.org/abs/2007.15528) (Li and Zhang, 2020) - [**Alleviating Privacy Attacks via Causal Learning**](https://arxiv.org/abs/1909.12732) (Tople et al., 2020) +- [**On the Effectiveness of Regularization Against Membership Inference Attacks**](https://arxiv.org/abs/2006.05336) (Kaya et al., 2020) - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) ## Reconstruction @@ -119,3 +120,5 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Reverse-Engineering Deep ReLU Networks**](https://proceedings.icml.cc/static/paper_files/icml/2020/1-Paper.pdf) (Rolnick and Kording, 2020) - [**Model Extraction Oriented Data Publishing with k-anonymity**](https://link.springer.com/chapter/10.1007/978-3-030-58208-1_13) (Fukuoka et al., 2020) - [**Hermes Attack: Steal DNN Models with Lossless Inference Accuracy**](https://arxiv.org/abs/2006.12784) (Zhu et al., 2020) +- [**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) From 75beb20f8227e92a1aa8e2ef1f7c7bdd4d24853c Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Tue, 8 Sep 2020 20:47:54 -0400 Subject: [PATCH 4/6] Add two membership inference papers --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 1b2f37d..ebcf2ac 100644 --- a/README.md +++ b/README.md @@ -54,6 +54,8 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Alleviating Privacy Attacks via Causal Learning**](https://arxiv.org/abs/1909.12732) (Tople et al., 2020) - [**On the Effectiveness of Regularization Against Membership Inference Attacks**](https://arxiv.org/abs/2006.05336) (Kaya et al., 2020) - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) +- [**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) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*. From 8c7b2bb10eb341da4d91497cc648c469bde358f1 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Tue, 8 Sep 2020 22:42:54 -0400 Subject: [PATCH 5/6] Add extraction paper --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index ebcf2ac..baf4211 100644 --- a/README.md +++ b/README.md @@ -124,3 +124,4 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Hermes Attack: Steal DNN Models with Lossless Inference Accuracy**](https://arxiv.org/abs/2006.12784) (Zhu et al., 2020) - [**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) From dd9812498799aa12c96ced7880bc34a0d950f67d Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Wed, 9 Sep 2020 00:21:14 -0400 Subject: [PATCH 6/6] Add another membership inference paper --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index baf4211..2e1fae2 100644 --- a/README.md +++ b/README.md @@ -56,6 +56,7 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Hide-and-Seek Privacy Challenge**](https://arxiv.org/abs/2007.12087) (Jordan et al., 2020) - [**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) ## Reconstruction Reconstruction attacks cover also attacks known as *model inversion* and *attribute inference*.