Membership Privacy in MicroRNA-based Studies

By Michael Backes, Pascal Berrang, Mathias Humbert, Praveen Manoharan. 2016

155 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Machine Learning Models that Remember Too Much (2017, background): “Subsequent work extended this work to published noisy statistics [24] and MicroRNA-based studies [5].”
Knock Knock, Who's There? Membership Inference on Aggregate Location Data (2017, background): “[2] show that membership inference can be mounted against individuals contributing their microRNA expressions to scientific studies.”
Auditing Data Provenance in Text-Generation Models (2018, background): “n D—and aims to determine whether a speciﬁc data record is a member of D. Successful membership inference attacks against aggregate statistics have been demonstrated in the context of genomic studies [3], [16], location time-series [28], and noisy statistics in general [9]. Membership inference atta”
LOGAN: Membership Inference Attacks Against Generative Models (2017, background): “Additional membership inference attacks focus on genomic research studies [24, 5], whereby an attacker aims to infer the presence of a particular individual’s data within an aggregate genomic dataset, or aggregate locations [50].”
Machine Learning with Membership Privacy using Adversarial Regularization (2018, background): “The membership inference attacks have mostly been studied for analyzing dataprivacy withrespecttosimple statisticallinear functions [5, 17, 18, 23, 42, 43].”
Membership Leakage in Label-Only Exposures (2020, background): “Membership inference attack has been successfully performed in various data domains, ranging form biomedical data [6, 22, 24] to mobility traces [43].”
Evaluating Differentially Private Machine Learning in Practice (2019, background): “[4] studied membership inference attacks on microRNA studies and showed that differential privacy can reduce the success of membership inference attacks, but at the cost of utility.”
Inference Attacks Against Collaborative Learning (2018, background): “, in the context of genomic studies [4, 25], location timeseries [42], or noisy statistics in general [14].”
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models (2019, background): “raining data. The resulting privacy breach would raise serious issues as training data contains sensitive attributes such as diagnosis and income. One such attack is membership inference attack (MIA) [5, 18, 24, 25, 58, 60] which aims to identify if a data record was used to train a machine learning”
Differentially Private Data Generative Models (2018, background): “Backes et al. [11] propose to conduct the membership inference attack against individuals contributing their microRNA expressions to scien-tiﬁc studies.”
MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples (2019, background): “Later, several works performed similar membership inference attacks against other types of biomedical data such as MicroRNA [4] and DNA methylation [20].”
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018, background): “Membership inference attack has been successfully performed in many different data domains, ranging form biomedical data [7], [20] to mobility traces [35].”
Enhanced Membership Inference Attacks against Machine Learning Models (2021, background): “[1, 28] provided a formal analysis of this risk of detecting the presence of an individual from aggregate statistics computed on independent (binary or continuous) attributes.”
The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model (2018, background): “Successful membership inference attacks against aggregate statistics have been demonstrated in the context of genomic studies [3], [16], location time-series [28], and noisy statistics in general [9].”
When Machine Unlearning Jeopardizes Privacy (2020, methodology): “rence between the two versions of the network embeddings. Membership Inference. Membership inference attacks have been extensively studied in many different data domains, ranging from biomedical data [5,22,26] to mobility traces [46]. Shokri et al. [54] presented the ﬁrst membership inference attack”
Membership Inference Attacks Against Machine Learning Models (2016, methodology): “By contrast, the membership inference problem we study in this paper is essentially the same as the well-known problem of identifying the presence of an individual’s data in a mixed pool given some statistics about the pool [3], [15], [21], [29].”
When Relaxations Go Bad: "Differentially-Private" Machine Learning (2019, unknown): “Moreover, Backes et al. [3] studied membership inference attacks on microRNA studies and showed that di ﬀ erential privacy can reduce the success of membership inference attacks, but at the cost of utility.”