DeepAI AI Chat
Log In Sign Up

Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release

by   Liam Fowl, et al.

Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge over their competitors. These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models. We solve this problem by developing a data poisoning method by which publicly released data can be minimally modified to prevent others from train-ing models on it. Moreover, our method can be used in an online fashion so that companies can protect their data in real time as they release it.We demonstrate the success of our approach onImageNet classification and on facial recognition.


KIBS Innovative Entrepreneurship Networks on Social Media

The analysis of the use of social media for innovative entrepreneurship ...

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

Facial recognition systems are increasingly deployed by private corporat...

Real-Time Inference of User Types to Assist with More Inclusive Social Media Activism Campaigns

Social media provides a mechanism for people to engage with social cause...

Invertible Image Dataset Protection

Deep learning has achieved enormous success in various industrial applic...

A Real-time System for Detecting Landslide Reports on Social Media using Artificial Intelligence

This paper presents an online system that leverages social media data in...

Learning more from crossing levels: Investigating agility at three levels of the organization

Scholars have tried to explain how organizations can build agile teams b...