English
Related papers

Related papers: Certifiably Robust Variational Autoencoders

200 papers

We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. While previous work has developed algorithmic approaches to attacking and defending VAEs, there…

Machine Learning · Statistics 2021-02-01 Alexander Camuto , Matthew Willetts , Stephen Roberts , Chris Holmes , Tom Rainforth

Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to defend against such attacks remains an open problem. We…

Machine Learning · Statistics 2021-02-01 Matthew Willetts , Alexander Camuto , Tom Rainforth , Stephen Roberts , Chris Holmes

In this work, we explore adversarial attacks on the Variational Autoencoders (VAE). We show how to modify data point to obtain a prescribed latent code (supervised attack) or just get a drastically different code (unsupervised attack). We…

Cryptography and Security · Computer Science 2021-05-07 Anna Kuzina , Max Welling , Jakub M. Tomczak

Recent work in adversarial attacks has developed provably robust methods for training deep neural network classifiers. However, although they are often mentioned in the context of robustness, deep generative models themselves have received…

Machine Learning · Computer Science 2020-04-23 Filipe Condessa , Zico Kolter

Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply…

Machine Learning · Statistics 2019-12-24 Haleh Akrami , Anand A. Joshi , Jian Li , Sergul Aydore , Richard M. Leahy

Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning. Our study focuses on a specific type of generative models - Variational Auto-Encoders (VAEs). Contrary to…

In this work we study Variational Autoencoders (VAEs) from the perspective of harmonic analysis. By viewing a VAE's latent space as a Gaussian Space, a variety of measure space, we derive a series of results that show that the encoder…

Machine Learning · Statistics 2022-04-26 Alexander Camuto , Matthew Willetts

Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a (nominally trained) VAE does not necessarily amortize…

Machine Learning · Computer Science 2020-12-08 A. Taylan Cemgil , Sumedh Ghaisas , Krishnamurthy Dvijotham , Sven Gowal , Pushmeet Kohli

Variational Autoencoders (VAEs) have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain largely underexplored. Although adversarial training has been an…

Machine Learning · Computer Science 2025-04-25 Hyomin Lee , Minseon Kim , Sangwon Jang , Jongheon Jeong , Sung Ju Hwang

Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic…

Machine Learning · Computer Science 2024-11-18 Chethan Krishnamurthy Ramanaik , Arjun Roy , Eirini Ntoutsi

In an unsupervised attack on variational autoencoders (VAEs), an adversary finds a small perturbation in an input sample that significantly changes its latent space encoding, thereby compromising the reconstruction for a fixed decoder. A…

Machine Learning · Computer Science 2024-10-29 Asif Khan , Amos Storkey

A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent…

Machine Learning · Computer Science 2017-11-21 Yunchen Pu , Weiyao Wang , Ricardo Henao , Liqun Chen , Zhe Gan , Chunyuan Li , Lawrence Carin

Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in downstream tasks such as classification. As previous work…

Machine Learning · Computer Science 2022-10-13 Anna Kuzina , Max Welling , Jakub M. Tomczak

We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variations. In this method, an adversarial network attempts to…

Machine Learning · Computer Science 2018-05-22 Ye Wang , Toshiaki Koike-Akino , Deniz Erdogmus

We propose a theoretical approach towards the training numerical stability of Variational AutoEncoders (VAE). Our work is motivated by recent studies empowering VAEs to reach state of the art generative results on complex image datasets.…

Machine Learning · Computer Science 2021-06-28 David Dehaene , Rémy Brossard

Variational Autoencoders (VAEs) have become increasingly popular and deployed in safety-critical applications. In such applications, we want to give certified probabilistic guarantees on performance under adversarial attacks. We propose a…

Machine Learning · Computer Science 2025-04-29 Changming Xu , Debangshu Banerjee , Deepak Vasisht , Gagandeep Singh

We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a…

Machine Learning · Computer Science 2020-03-27 Robert Sicks , Ralf Korn , Stefanie Schwaar

The generative autoencoders, such as the variational autoencoders or the adversarial autoencoders, have achieved great success in lots of real-world applications, including image generation, and signal communication. However, little concern…

Machine Learning · Computer Science 2023-07-06 Mingfei Lu , Badong Chen

Deep neural networks are known to be vulnerable to adversarial attacks. This exposes them to potential exploits in security-sensitive applications and highlights their lack of robustness. This paper uses a variational auto-encoder (VAE) to…

Computer Vision and Pattern Recognition · Computer Science 2018-12-10 Yi Luo , Henry Pfister

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. We develop three variations on VAEs by introducing a second parameterized encoder/decoder pair and,…

Machine Learning · Computer Science 2023-04-06 R. I. Cukier
‹ Prev 1 2 3 10 Next ›