Adversarial training improves graph autoencoder generalization.
problem Improving graph autoencoder generalization.
method Formulated L2 and L1 adversarial training for graph autoencoders and variational graph autoencoders.
result Adversarial training boosts graph autoencoder and variational graph autoencoder generalization.
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
problem Addressing mode collapse and likelihood issues in GANs and autoencoders.
method Explains various GAN and autoencoder variants, their applications, and methods to resolve issues.
result Various methods to resolve mode collapse and improve likelihood in GANs and autoencoders.
A new autoencoder uses stochastic functions to encourage diversity in generated samples.
problem Generating diverse samples from autoencoders.
method Replacing the adversary in AAE with a space of stochastic functions.
result More diverse set of generated samples.
A cascaded autoencoder defends machine learning models from adversarial attacks.
problem Adversarial attacks on machine learning models.
method Denoising and dimensionality reduction using cascaded autoencoders.
result Preprocessed data with cascaded autoencoder pipeline improves model accuracy against adversarial perturbations.
Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.
problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.
Advances citation and subject label recommendation using multi-modal adversarial autoencoders.
problem Improving recommendation systems for citations and subject labels.
method Multi-modal adversarial autoencoders with adversarial regularization, sparsity, and input modality analysis.
result Adversarial regularization consistently improves recommendation performance.
Detects adversarial examples using autoencoders at hidden layers.
problem Identifying adversarial examples in deep neural networks.
method Trains autoencoders on intermediate layers to detect deviations from true data.
result Outperforms state-of-the-art methods in both supervised and unsupervised settings.
Adversarial autoencoders improve speech-based emotion recognition.
problem Improving speech-based emotion recognition accuracy.
method Adversarial autoencoders map feature vectors to different noise PDFs, allowing synthetic sample generation.
result Adversarial autoencoders can encode high-dimensional feature vectors into a compressed space with minimal loss of emotion class discriminability.
CASS separates mixed signals using autoencoders and adversarial learning.
problem Separating mixed signals into individual components.
method Cross adversarial source separation via autoencoder framework.
result State-of-the-art performance in separating components with similar data structures.
A new VAE variant connects to adversarial learning.
problem Learning limitations in VAE and adversarial methods.
method Symmetric Kullback-Leibler divergence in VAE.
result Unified approach to VAE and adversarial learning.
Adversarial autoencoder improves music latent space learning.
problem Learning effective latent spaces for symbolic music data.
method Adversarial regularization with Gaussian mixtures.
result MusAE outperforms standard VAEs in reconstruction and interpolation.
New method uses adversarial networks to improve image quality in autoencoders.
problem Blurriness in autoencoder-generated images due to Gaussian assumptions.
method Integrates adversarial networks to optimize parameters without Gaussian assumptions.
result Improves image quality by allowing better representation of multimodal distributions.
QGAA learns latent quantum states, reducing errors in quantum data generation.
problem Learning latent representations for quantum data generation.
method Quantum Generative Adversarial Autoencoder (QGAA) combining QAE and QGAN.
result Average errors in energies for H2 and LiH are 0.02 Ha and 0.06 Ha respectively, demonstrating QGAA's potential.
Adversarial autoencoders improve anomaly detection in images.
problem Anomaly detection in images is challenging when training data contains outliers.
method Adversarial autoencoders enforce a prior distribution on latent representations to identify and reject potential anomalies during training.
result Adversarial autoencoders significantly improve robustness to outliers during training.
Improves autoencoder reconstruction quality by approximating latent space with adversarial learning.
problem Ambiguity in autoencoder reconstructions and difficulty in matching true distribution.
method Adversarially Approximated Autoencoder (AAAE) using GAN for flexible latent space approximation.
result Generates more faithful reconstructions and maintains latent manifold structure.
RevNets improve generative performance on CelebA dataset.
problem Training autoencoders is complicated by needing separate encoder and decoder models.
method Used adversarial autoencoder framework with RevNets in latent space.
result RevNets generate coherent faces with similar quality to Variational Autoencoders.
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space. More robust r…
Improved anomaly detection using adversarial mirrored autoencoders.
problem Detecting out-of-distribution samples in machine learning.
method Adversarial Mirrored Autoencoder (AMA) with latent space regularization.
result AMA improves anomaly detection performance on OOD detection benchmarks.
OGAN attacks autoencoders to prevent deepfake creation.
problem Preventing deepfake creation using adversarial attacks.
method Training-resistant adversarial attack on face-swapping autoencoders.
result OGAN attacks are training-resistant and transfer across different models and faces.
Generative model improves latent space convexity through adversarial training on interpolations.
problem Improving latent space convexity in generative models.
method Adversarial training on latent space interpolations within an AE-GAN architecture.
result Convex latent distribution of generated images, preserving realistic resemblances.
Pre-training deep RF classifiers with autoencoders mitigates adversarial attacks.
problem Adversarial examples in RF deep learning cause targeted misclassifications.
method Pre-training the classifier using an autoencoder.
result Pre-training method validates as a viable mitigation against adversarial attacks.
Paper proposes a new graph embedding framework to improve graph analytics.
problem Graph embedding often fails to capture the distribution of latent codes.
method Adversarial graph autoencoder framework that combines topological structure and node content.
result ARGA and ARVGA outperform baselines in link prediction, clustering, and visualization.
3D Adversarial Autoencoder learns compact binary descriptors from 3D point clouds.
problem Learning meaningful representations of 3D shapes for various tasks.
method End-to-end Adversarial Autoencoder model trained on 3D input and output.
result 3D Adversarial Autoencoder (3dAAE) generates state-of-the-art results for 3D points clustering and retrieval.
DefenseVGAE defends graph neural networks against adversarial attacks.
problem Vulnerability of GNNs to adversarial structural perturbations.
method Variational Graph Autoencoder (VGAE) to reconstruct graph structure.
result DefenseVGAE reduces adversarial perturbations and boosts GCN performance.
This paper proposes learning priors for adversarial autoencoders to improve model expressiveness.
problem The choice of priors in deep latent factor models can significantly affect model expressiveness, especially for models with limited capacity.
method The authors introduce code generators to transform simple priors into ones that better characterize the data distribution for adversarial autoencoders.
result The proposed model generates better image quality and learns better disentangled representations than standard AAEs in supervised and unsupervised settings.
The paper detects adversarial examples in LECs for regression in CPS using variational autoencoder.
problem Detecting adversarial examples in learning-enabled cyber-physical systems (CPS).
method Inductive conformal prediction using a variational autoencoder regression model.
result The method effectively detects adversarial examples with a short delay in an emergency braking system simulation.
VAEs are vulnerable to adversarial attacks; new methods improve their robustness.
problem Vulnerability of VAEs to adversarial attacks.
method Introducing methods for producing adversarially robust VAEs, including disentangling latent representations and applying them to hierarchical VAEs.
result Hierarchical VAEs produce high-fidelity autoencoders that are also adversarially robust.
Paper proposes a novel adversarial framework for graph embedding.
problem Graph embedding often fails to represent latent codes effectively.
method Adversarial training to enforce latent codes to match a prior distribution.
result ARGA and ARVGA models improve graph embedding for link prediction and clustering.
New molecular design model outperforms existing methods.
problem Designing valid, unique, and novel molecules.
method Adversarially Regularized Autoencoder (ARAE) combining latent variables from VAE and adversarial training from GAN.
result ARAE outperforms conventional models in validity, uniqueness, and novelty.
A CAE improves DNN's outlier and adversary defense.
problem Improving DNN's robustness against outliers and adversaries.
method Proposes a classification-autoencoder (CAE) that compresses samples into disjoint spaces and uses a decoder to classify and defend against adversaries.
result The CAE achieves state-of-the-art outlier recognition and near-lossless classification of adversaries.
PuVAE purifies adversarial examples by projecting them onto class manifolds.
problem Vulnerability of deep neural networks to adversarial attacks.
method PuVAE purifies adversarial examples by projecting them onto the manifold of each class.
result PuVAE purifies adversarial examples effectively without prior knowledge of the attack.
A new autoencoder learns expressive posterior and conditional likelihood distributions.
problem Learning more expressive posterior and conditional likelihood distributions.
method Implicit autoencoder using two generative adversarial networks for reconstruction and regularization.
result Implicit autoencoder can disentangle content and style information.
Unified framework resists adversarial and fooling samples.
problem Vulnerability of deep neural networks to adversarial attacks.
method Gaussian mixture variational autoencoder with selective classification.
result Selective classification rejects adversarial samples.
AAANE embeds networks by learning attention weights for multi-scale structure.
problem Existing methods ignore the role of different scales in network embedding.
method AAANE uses an attention-based adversarial autoencoder to learn robust representations.
result AAANE outperforms existing methods on real-world networks.
This work proposes a novel autoencoder for fusing visible and infrared images.
problem Challenging task to combine spatial and spectral information from visible and infrared images.
method Spatially constrained adversarial autoencoder with residual architecture and adversarial regularizer.
result Generates a more realistic fused image with enhanced spatial and spectral information.
Proposes AEGAN for stable GAN training.
problem Training instability in GANs.
method Four-network model with adversarial and reconstruction losses.
result Stabilizes GAN training and prevents mode-collapse.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
problem Clustering autoencoders learn unreliable pseudo-labels, distorting latent space and feature randomness.
method Adversarial training to balance reconstruction loss and clustering objective.
result ADEC outperforms state-of-the-art autoencoder-based clustering methods.
Study shows how to manipulate VAEs for attacks and assess their robustness.
problem Adversarial attacks on Variational Autoencoders (VAE).
method Examine modifications to VAEs and propose metrics for robustness.
result Metrics to quantify the robustness of VAEs to adversarial attacks.
Proposes a self-adversarial variational autoencoder for anomaly detection.
problem Anomaly detection in deep generative models.
method Self-adversarial Variational Autoencoder with Gaussian anomaly prior.
result Significant improvements in anomaly detection performance compared to SOTA baselines.
Regularizes autoencoders to improve interpolation quality and downstream performance.
problem Improving autoencoder interpolation quality and downstream performance.
method Adversarial regularization to fool a critic network trained on interpolated data.
result Our regularizer dramatically improves interpolation quality and downstream performance.
Generative models use autoencoders to learn manifold structures.
problem Learning a manifold structure on datasets.
method Adversarial/Wasserstein autoencoders for deep neural networks.
result Atlas of a manifold formed from dimensionality reduction and fuzzy clustering.
Paper studies autoencoder-based anomaly detectors' robustness to adversarial poisoning attacks.
problem Adversarial poisoning attacks on online-trained autoencoder-based anomaly detectors in ICSs.
method Proposes two algorithms for generating poison samples and evaluates them on synthetic and real-world ICS data.
result Autoencoder detectors are resilient to poisoning in the face of all relevant attacks in the SWaT dataset.
This paper explores using SSIM for better image generation in generative models.
problem Improving perceptual quality in generated images using ℓ2 norm. method Theoretical discussion and practical implementation of SSIM in generative models and autoencoders.
result SSIM can be used in generative models and autoencoders to generate better images.
Paper proposes a new method for predicting drug interactions using adversarial autoencoders.
problem Predicting drug interactions to prevent adverse events.
method Introduces adversarial autoencoders based on Wasserstein distances and Gumbel-Softmax relaxation to generate high-quality negative samples.
result Significant improvements in link prediction and DDI classification tasks.
S2SNets defend against adversarial attacks by interpreting perturbations as signal.
problem Fragility of deep neural networks to adversarial attacks.
method Two-stage training of S2SNets: unsupervised first, fine-tuning second, using classifier gradients.
result S2SNets achieve comparable resilience in white-box attacks and robustness in gray-box attacks.
Adversarial autoencoder networks detect accounting anomalies in latent space.
problem Detecting fraud in accounting data using handcrafted rules that fail to generalize.
method Adversarial autoencoder neural networks to learn semantic meaningful representations.
result The learned representation improves anomaly detection and interpretability.
Combines VAE and adversarial censoring for invariant representations.
problem Learning invariant representations from data with nuisance variables.
method Adversarial censoring in conditional VAEs to prevent nuisance variable recovery.
result Achieves invariance while preserving model learning performance.
Adversarial autoencoder learns data on curved manifolds.
problem Representing data with non-Euclidean geometry.
method CCM adversarial autoencoder (CCM-AAE) trained on constant-curvature Riemannian manifolds.
result CCM-AAE outperforms other autoencoders on non-Euclidean data.