Knowledge-Enriched Distributional Model Inversion Attacks
Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing MI attacks against deep neural networks (DNNs) have large room for performance improvement. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. In particular, we train the discriminator to differentiate not only the real and fake samples but the soft-labels provided by the target model. Moreover, unlike previous work that directly searches for a single data point to represent a target class, we propose to model a private data distribution for each target class. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%, and generalize better to a variety of datasets and models. Our code is available at https://github.com/SCccc21/Knowledge-Enriched-DMI.
Code (2)
Tasks
modelSimilar Papers 제목 키워드 기반
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research ha…
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that traini…
Face RecognitionregressionGI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge
Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion…
Federated LearningPrivacy PreservingText Embedding Inversion Security for Multilingual Language Models
Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddi…
Reinforcement Learning-Based Black-Box Model Inversion Attacks
Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative…
modelPrivacy Preservingreinforcement-learningReinforcement Learning