Tight Lower Bounds for Differentially Private Selection (2017, background): “Relationship to Previous Lower Bounds and Attacks Our argument is closely related to the work on tracing attacks [29], [30], [16], [17], [18], [26], [31].”
Machine Learning with Membership Privacy using Adversarial Regularization (2018, background): “In particular, an adversary, with even black-box access to a model, can perform a membership inference [23, 43] (also known as the tracing [17]) attack against the model to determine whether or not a target data record is a member of its training set [45].”
Fingerprinting codes and the price of approximate differential privacy (2013, neutral): “Dwork et al. [DSS+15] observe that the privacy attack implicit in our negative results is closely related to the in uential attacks that were employed by Homer et al. [HSR+08] (and further studied in [SOJH09]) to violate privacy of public genetic datasets. Using this connection, they show how to mak”
Information Leakage in Embedding Models (2020, background): “Applying a line of research investigating whether individual genomic records can be subsequently identified [28, 62], Shokri et al.”
Privacy-Preserving Data Sharing for Genome-Wide Association Studies (2012, background): “Others have criticized Homer et al., suggested alternative formulations of the identification problem, claimed to strengthen the attack or suggested different ways to protect the data, e.g., see [6, 13, 14, 15, 17, 18, 20, 22, 26].”
Dissecting the genetics of complex traits using summary association statistics (2016, unknown): “…privacy attacks have low power when the summary sample size exceeds the effective number of independent markers (currently estimated at 60,000 in typical GWAS data sets 104 ), implying that privacy concerns should not preclude the public release of summary statistics from large studies 105-107 .”
Enhanced Membership Inference Attacks against Machine Learning Models (2021, background): “This attack is also very similar to the membership inference attacks designed for summary statistics and graphical models, which use reference models to compute the probability of the null hypothesis [22, 29].”