Reducing audio membership inference attack accuracy to chance: 4 defenses

10/31/2019
by   Michael Lomnitz, et al.
0

It is critical to understand the privacy and robustness vulnerabilities of machine learning models, as their implementation expands in scope. In membership inference attacks, adversaries can determine whether a particular set of data was used in training, putting the privacy of the data at risk. Existing work has mostly focused on image related tasks; we generalize this type of attack to speaker identification on audio samples. We demonstrate attack precision of 85.9% and recall of 90.8% for LibriSpeech, and 78.3% precision and 90.7% recall for VOiCES (Voices Obscured in Complex Environmental Settings). We find that implementing defenses such as prediction obfuscation, defensive distillation or adversarial training, can reduce attack accuracy to chance.

READ FULL TEXT
research
06/15/2019

Reconciling Utility and Membership Privacy via Knowledge Distillation

Large capacity machine learning models are prone to membership inference...
research
09/01/2020

Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries

Machine learning models have been shown to leak information violating th...
research
05/12/2021

Accuracy-Privacy Trade-off in Deep Ensembles

Deep ensemble learning has been shown to improve accuracy by training mu...
research
02/20/2019

Under the Hood of Membership Inference Attacks on Aggregate Location Time-Series

Aggregate location statistics are used in a number of mobility analytics...
research
03/07/2023

Can Membership Inferencing be Refuted?

Membership inference (MI) attack is currently the most popular test for ...
research
02/28/2023

Membership Inference Attack for Beluga Whales Discrimination

To efficiently monitor the growth and evolution of a particular wildlife...
research
02/10/2022

A Note on the Misinterpretation of the US Census Re-identification Attack

In 2018, the US Census Bureau designed a new data reconstruction and re-...

Please sign up or login with your details

Forgot password? Click here to reset