Canary Extraction in Natural Language Understanding Models

by   Rahil Parikh, et al.

Natural Language Understanding (NLU) models can be trained on sensitive information such as phone numbers, zip-codes etc. Recent literature has focused on Model Inversion Attacks (ModIvA) that can extract training data from model parameters. In this work, we present a version of such an attack by extracting canaries inserted in NLU training data. In the attack, an adversary with open-box access to the model reconstructs the canaries contained in the model's training set. We evaluate our approach by performing text completion on canaries and demonstrate that by using the prefix (non-sensitive) tokens of the canary, we can generate the full canary. As an example, our attack is able to reconstruct a four digit code in the training dataset of the NLU model with a probability of 0.5 in its best configuration. As countermeasures, we identify several defense mechanisms that, when combined, effectively eliminate the risk of ModIvA in our experiments.


page 1

page 2

page 3

page 4


Extracting Training Data from Large Language Models

It has become common to publish large (billion parameter) language model...

GAMIN: An Adversarial Approach to Black-Box Model Inversion

Recent works have demonstrated that machine learning models are vulnerab...

Black-box Model Inversion Attribute Inference Attacks on Classification Models

Increasing use of ML technologies in privacy-sensitive domains such as m...

Federated Distillation of Natural Language Understanding with Confident Sinkhorns

Enhancing the user experience is an essential task for application servi...

Property Unlearning: A Defense Strategy Against Property Inference Attacks

During the training of machine learning models, they may store or "learn...

Active Data Pattern Extraction Attacks on Generative Language Models

With the wide availability of large pre-trained language model checkpoin...

Label-only Model Inversion Attack: The Attack that Requires the Least Information

In a model inversion attack, an adversary attempts to reconstruct the da...