From c905ffd275436ba6700446785ed01cbdf5f69706 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Sat, 2 Jul 2022 15:22:09 -0400 Subject: [PATCH 1/4] Add "Membership Inference via Backdooring" --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index cb79845..d164375 100755 --- a/README.md +++ b/README.md @@ -98,6 +98,7 @@ A curated list of membership inference papers (more than 100 papers) on machine - [**TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing**](https://arxiv.org/abs/2107.13190) (Hu et al., 2021) - [**Enhanced Membership Inference Attacks against Machine Learning Models**](https://arxiv.org/abs/2111.09679) (Ye et al., 2021) - [**Do Not Trust Prediction Scores for Membership Inference Attacks**](https://arxiv.org/abs/2111.09076) (Hintersdorf et al., 2021) +- [**Membership Inference via Backdooring**](https://arxiv.org/abs/2206.04823) (Hu et al. 2022) From f3bc8ba4c090ed154e045e2158631e37b2e44939 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Sat, 2 Jul 2022 15:29:31 -0400 Subject: [PATCH 2/4] Add "The Privacy Onion Effect" --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index d164375..c98e890 100755 --- a/README.md +++ b/README.md @@ -255,3 +255,4 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**Bounding Information Leakage in Machine Learning**](https://arxiv.org/abs/2105.03875) (Del Grosso et al., 2021) - [**RoFL: Attestable Robustness for Secure Federated Learning**](https://arxiv.org/abs/2107.03311) (Burkhalter et al., 2021) - [**Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash**](https://arxiv.org/abs/2111.06628) (Struppek et al., 2021) +- [**The Privacy Onion Effect: Memorization is Relative**](https://arxiv.org/abs/2206.10469) (Carlini et al., 2022) From fdad99ebfaf7a1d58f0de527fb229d79f89c9f75 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Sat, 2 Jul 2022 15:31:01 -0400 Subject: [PATCH 3/4] Add "I Know What You Trained Last Summer" --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c98e890..035bb61 100755 --- a/README.md +++ b/README.md @@ -23,6 +23,7 @@ This repository contains a curated list of papers related to privacy attacks aga - [**Survey: Leakage and Privacy at Inference Time**](https://arxiv.org/abs/2107.01614) (Jegorova et al., 2021) - [**A Review of Confidentiality Threats Against Embedded Neural Network Models**](https://arxiv.org/abs/2105.01401) (Joud et al., 2021) - [**Federated Learning Attacks Revisited: A Critical Discussion of Gaps,Assumptions, and Evaluation Setups**](https://arxiv.org/abs/2111.03363) (Wainakh et al., 2021) +- [**I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences**](https://arxiv.org/abs/2206.08451) (Oliynyk et al., 2022) # Privacy Testing Tools - [**PrivacyRaven**](https://github.com/trailofbits/PrivacyRaven) (Trail of Bits) From 3bb4cace4d8dae68df6b7fcc7207e989fc01f6e0 Mon Sep 17 00:00:00 2001 From: Suha Sabi Hussain Date: Sat, 2 Jul 2022 16:21:28 -0400 Subject: [PATCH 4/4] Add "Truth Serum" --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 035bb61..3cf1f12 100755 --- a/README.md +++ b/README.md @@ -257,3 +257,4 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib - [**RoFL: Attestable Robustness for Secure Federated Learning**](https://arxiv.org/abs/2107.03311) (Burkhalter et al., 2021) - [**Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash**](https://arxiv.org/abs/2111.06628) (Struppek et al., 2021) - [**The Privacy Onion Effect: Memorization is Relative**](https://arxiv.org/abs/2206.10469) (Carlini et al., 2022) +- [**Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets**](https://arxiv.org/abs/2204.00032) (Tramer et al., 2022)