Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
arXiv:2103.02683
Abstract
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.
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Language Models are Few-Shot Learners
- Densely Connected Convolutional Networks
- Embedding Watermarks into Deep Neural Networks
- Is feature selection secure against training data poisoning?
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Stronger Data Poisoning Attacks Break Data Sanitization Defenses
- MetaPoison: Practical General-purpose Clean-label Data Poisoning
- On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
- Understanding Generalization through Visualizations
- LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
Cited by in corpus (6)
- Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
- Adversarial Examples Make Strong Poisons
- Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
- Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
- Fooling Adversarial Training with Inducing Noise
- Disrupting Model Training with Adversarial Shortcuts