Adversarial Data Encryption

Abstract

In the big data era, many organizations face the dilemma of data sharing. Regular data sharing is often necessary for human-centered discussion and communication, especially in medical scenarios. However, unprotected data sharing may also lead to data leakage. Inspired by adversarial attack, we propose a method for data encryption, so that for human beings the encrypted data look identical to the original version, but for machine learning methods they are misleading. To show the effectiveness of our method, we collaborate with the Beijing Tiantan Hospital, which has a world leading neurological center. We invite $3$ doctors to manually inspect our encryption method based on real world medical images. The results show that the encrypted images can be used for diagnosis by the doctors, but not by machine learning methods.

References in corpus (15)

• Deep Learning with Differential Privacy
• mixup: Beyond Empirical Risk Minimization
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Robust Physical-World Attacks on Deep Learning Models
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• Adversarial examples from computational constraints
• Do CIFAR-10 Classifiers Generalize to CIFAR-10?
• Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
• Adversarial Spheres
• Defending Against Adversarial Attacks by Leveraging an Entire GAN
• Adversarial Music: Real World Audio Adversary Against Wake-word Detection System