arXiv research

New method enhances neural network robustness against adversarial attacks.

Study shows how to manipulate VAEs for attacks and assess their robustness.

DefenseVGAE defends graph neural networks against adversarial attacks.

Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational O…

The paper detects adversarial examples in LECs for regression in CPS using variational autoencoder.

Adversarial training improves graph autoencoder generalization.

A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techni…

SVAT reduces investment risks by making stock models sensitive to adversarial perturbations.

Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.

Improved IFA with Generative Adversarial Networks for high-dimensional latent variables.

Adversarial CCA improves representation learning by allowing more flexible priors.

We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably improves both the generalization and robustness of DNN. In the CIFAR10 benchmark, we raise the robust accuracy of the adversarially trained Res…

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…

This paper combines three techniques to reduce communications in distributed variational inequalities.

Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN objective. Yet, surprisingly few studies have looked at optimization methods desi…

Paper proposes robust generative models using VAEs.

The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based unsupervised clustering or semi-supervised classification. Combining the power of these two generative models, we introduce Multi-Adversarial Variational autoEncoder Networ…

Improved reliability of machine learning predictions using variational auto-encoders.

Paper generates diverse, readable adversarial texts from scratch.

Generative model simulates financial market price variations from order flow.

VERA uses variational inference to jailbreak LLMs without manual optimization.

Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success. Two distinct categories of samples to which deep networks are vulnerable, "adversarial samples" and "fooling samples", have b…

Robust RL improves controller robustness to dynamics variations using adversarial populations.

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 recover the nuisance variable from the representation, which the VAE is trained to pre…

This paper analyzes $β$-Variational Classifiers for robustness and adversarial perturbation detection.

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific…

Adversarial autoencoder improves music latent space learning.

The paper learns perturbation sets from data to improve robustness in machine learning.

New deep learning model robust to adversarial attacks using stochastic LWTA units.

We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…

The study improves PAC-Bayesian bounds for adversarial generative models.

The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approx…

The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.

This paper shows equivalence between SVGD and BBVI using kernel gradient flows.

Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the ava…

New geometric insights reveal properties of adversarial training problems.

Improves GANs training through game theory.

AutoBayes automates Bayesian graph exploration for robust machine learning.

Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling mechanism in an adversarial manner. Unlike conventional active learning algorithms, o…

Study adversarial classification with data corruption up to ε, deriving geometric flows.

This work improves disentanglement by preventing style variables from encoding content-related features.

Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions …

Half-AVAE enhances VAE for underdetermined ICA with adversarial training.

Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for vari…

Unbalanced GANs stabilize GAN training by pre-training the generator with VAE.

TA-VAAL improves active learning by better utilizing task structures and overall data distribution.

In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networ…

Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propose an attack methodology not only for cases where the perturbations are measured by $\ell_p$ norms, but in fact any adversarial dissimilarit…