Model Extraction and Defenses on Generative Adversarial Networks
arXiv:2101.02069
Abstract
Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against generative models are less well explored. In this paper, we systematically study the feasibility of model extraction attacks against generative adversarial networks (GANs). Specifically, we first define accuracy and fidelity on model extraction attacks against GANs. Then we study model extraction attacks against GANs from the perspective of accuracy extraction and fidelity extraction, according to the adversary's goals and background knowledge. We further conduct a case study where an adversary can transfer knowledge of the extracted model which steals a state-of-the-art GAN trained with more than 3 million images to new domains to broaden the scope of applications of model extraction attacks. Finally, we propose effective defense techniques to safeguard GANs, considering a trade-off between the utility and security of GAN models.
References in corpus (17)
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Deep Learning with Differential Privacy
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Language Models are Few-Shot Learners
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Improved Techniques for Training GANs
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Passage Re-ranking with BERT
- GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
- Generative Visual Manipulation on the Natural Image Manifold
- Entangled Watermarks as a Defense against Model Extraction
- Discriminator Rejection Sampling
- Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
- Towards Security Threats of Deep Learning Systems: A Survey
- Model Extraction Attacks against Recurrent Neural Networks
- Stealing Deep Reinforcement Learning Models for Fun and Profit