Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources

07/17/2020
by   Yun-Yun Tsai, et al.
79

Current transfer learning methods are mainly based on finetuning a pretrained model with target-domain data. Motivated by the techniques from adversarial machine learning (ML) that are capable of manipulating the model prediction via data perturbations, in this paper we propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box ML model (e.g., a prediction API or a proprietary software) for solving different ML tasks, especially in the scenario with scarce data and constrained resources. The rationale lies in exploiting high-performance but unknown ML models to gain learning capability for transfer learning. Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a black-box ML model solely based on its input-output responses without knowing the model architecture or changing any parameter. More importantly, in the limited medical data setting, on autism spectrum disorder classification, diabetic retinopathy detection, and melanoma detection tasks, BAR outperforms state-of-the-art methods and yields comparable performance to the vanilla adversarial reprogramming method requiring complete knowledge of the target ML model. BAR also outperforms baseline transfer learning approaches by a significant margin, demonstrating cost-effective means and new insights for transfer learning.

READ FULL TEXT

page 2

page 13

08/25/2020

Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning

Transfer learning has become a common practice for training deep learnin...
07/10/2022

Scaling up ML-based Black-box Planning with Partial STRIPS Models

A popular approach for sequential decision-making is to perform simulato...
05/09/2020

Estimating g-Leakage via Machine Learning

This paper considers the problem of estimating the information leakage o...
08/15/2019

Multitask and Transfer Learning for Autotuning Exascale Applications

Multitask learning and transfer learning have proven to be useful in the...
02/23/2020

Stealing Black-Box Functionality Using The Deep Neural Tree Architecture

This paper makes a substantial step towards cloning the functionality of...
04/26/2021

Improving Botnet Detection with Recurrent Neural Network and Transfer Learning

Botnet detection is a critical step in stopping the spread of botnets an...
02/04/2019

F-BLEAU: Fast Black-box Leakage Estimation

We consider the problem of measuring how much a system reveals about its...