Collaborating Authors

Reconstructing Training Data from Diverse ML Models by Ensemble Inversion Artificial Intelligence

Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the trained model under attack (MUA) is usually frozen and used to guide the training of a generator, such as a Generative Adversarial Network (GAN), to reconstruct the distribution of the original training data of that model. This might cause leakage of original training samples, and if successful, the privacy of dataset subjects will be at risk if the training data contains Personally Identifiable Information (PII). Therefore, an in-depth investigation of the potentials of MI techniques is crucial for the development of corresponding defense techniques. High-quality reconstruction of training data based on a single model is challenging. However, existing MI literature does not explore targeting multiple models jointly, which may provide additional information and diverse perspectives to the adversary. We propose the ensemble inversion technique that estimates the distribution of original training data by training a generator constrained by an ensemble (or set) of trained models with shared subjects or entities. This technique leads to noticeable improvements of the quality of the generated samples with distinguishable features of the dataset entities compared to MI of a single ML model. We achieve high quality results without any dataset and show how utilizing an auxiliary dataset that's similar to the presumed training data improves the results. The impact of model diversity in the ensemble is thoroughly investigated and additional constraints are utilized to encourage sharp predictions and high activations for the reconstructed samples, leading to more accurate reconstruction of training images.

Secretary Ranking with Minimal Inversions

Neural Information Processing Systems

We study a secretary problem which captures the task of ranking in online settings. We term this problem the secretary ranking problem: elements from an ordered set arrive in random order and instead of picking the maximum element, the algorithm is asked to assign a rank, or position, to each of the elements. The rank assigned is irrevocable and is given knowing only the pairwise comparisons with elements previously arrived. The goal is to minimize the distance of the rank produced to the true rank of the elements measured by the Kendall-Tau distance, which corresponds to the number of pairs that are inverted with respect to the true order. Our main result is a matching upper and lower bound for the secretary ranking problem.

Membership Model Inversion Attacks for Deep Networks Machine Learning

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of instancesused to train the targeted machine learning model. This so-called model inversionattack is based on sequential leveraging of classification scores towards obtaininghigh confidence representations for various classes. However, for deep networks,such procedures usually lead to unrecognizable representations that are uselessfor the adversary. In this paper, we introduce a more realistic definition of modelinversion, where the adversary is aware of the general purpose of the attackedmodel (for instance, whether it is an OCR system or a facial recognition system),and the goal is to find realistic class representations within the corresponding lower-dimensional manifold (of, respectively, general symbols or general faces). To thatend, we leverage properties of generative adversarial networks for constructinga connected lower-dimensional manifold, and demonstrate the efficiency of ourmodel inversion attack that is carried out within that manifold.

WATCH LIVE: Obama to address new rules to deter tax inversions at 12:15 p.m. EDT

PBS NewsHour

President Barack Obama will speak from the White House about new rules aimed at deterring "tax inversions." The White House says Obama will speak at 12:15 p.m. in the Brady Press Briefing Room. His remarks come a day after the Treasury Department announced a package of steps designed to make inversions less financially appealing. Tax inversions occur when companies move abroad for lower tax rates. The use of inversions has sparked a political outcry.

Why Use Ensemble Learning?


What are the Benefits of Ensemble Methods for Machine Learning? Ensembles are predictive models that combine predictions from two or more other models. Ensemble learning methods are popular and the go-to technique when the best performance on a predictive modeling project is the most important outcome. Nevertheless, they are not always the most appropriate technique […]