Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial noise. In this study, we propose specific generators, defined Multiple Latent Variable Generative Models (MLVGMs), for adversarial purification. These models possess multiple latent variables that naturally disentangle coarse from fine features. Taking advantage of these properties, we autoencode images to maintain class-relevant information, while discarding and re-sampling any detail, including adversarial noise. The procedure is completely training-free, exploring the generalization abilities of pre-trained MLVGMs on the adversarial purification downstream task. Despite the lack of large models, trained on billions of samples, we show that smaller MLVGMs are already competitive with traditional methods, and can be used as foundation models. Official code released at https://github.com/SerezD/gen_adversarial.
Code (1)
Tasks
Adversarial PurificationSimilar Papers 제목 키워드 기반
Avoiding Latent Variable Collapse With Generative Skip Models
Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture…
Reweighted Wake-Sleep
Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been pr…
A moment-matching metric for latent variable generative models
It can be difficult to assess the quality of a fitted model when facing unsupervised learning problems. Latent variable models, such as variation autoencoders and Gaussian mixture models, are often trained with likelihoo…
Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data
Training generative models that capture rich semantics of the data and interpreting the latent representations encoded by such models are very important problems in un-/self-supervised learning. In this work, we provide …
AttributeCausal Discoveryfeature selectionSelf-Supervised Learning+1A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation
In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer and local details (e.g., StyleGAN, NVAE)…
Image GenerationRepresentation LearningSelf-Supervised Learning